Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3238 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.3853. Min Range: -11.3853
Max Act: 11.3853. Min Act: -0.1700
Data Index: 7423155 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3853. Min Range: -11.3853
Max Act: 11.3853. Min Act: -0.1700
Data Index: 556462 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3853. Min Range: -11.3853
Max Act: 11.3228. Min Act: -0.1700
Data Index: 4141931 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3853. Min Range: -11.3853
Max Act: 11.2603. Min Act: -0.1700
Data Index: 7148656 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3853. Min Range: -11.3853
Max Act: 11.1353. Min Act: -0.1700
Data Index: 3805456 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3853. Min Range: -11.3853
Max Act: 11.1353. Min Act: -0.1700
Data Index: 7000520 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3853. Min Range: -11.3853
Max Act: 11.0728. Min Act: -0.1700
Data Index: 2408898 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3853. Min Range: -11.3853
Max Act: 11.0728. Min Act: -0.1700
Data Index: 733131 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.9478. Min Act: -0.1700
Data Index: 1144220 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.9478. Min Act: -0.1700
Data Index: 7920855 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.9478. Min Act: -0.1700
Data Index: 7058857 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.9478. Min Act: -0.1700
Data Index: 8823864 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.8853. Min Act: -0.1700
Data Index: 6754804 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.8853. Min Act: -0.1700
Data Index: 8167401 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.8228. Min Act: -0.1700
Data Index: 5245728 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.8853. Min Act: -0.1700
Data Index: 5965666 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.8228. Min Act: -0.1700
Data Index: 5686373 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.7603. Min Act: -0.1700
Data Index: 224939 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.8228. Min Act: -0.1700
Data Index: 2527716 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3853. Min Range: -11.3853
Max Act: 10.8228. Min Act: -0.1700
Data Index: 7472669 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #19