Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 463 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.2975. Min Act: -0.1700
Data Index: 3181778 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.2661. Min Act: -0.1700
Data Index: 6529958 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.2504. Min Act: -0.1700
Data Index: 4090868 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.2504. Min Act: -0.1700
Data Index: 2558830 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.2190. Min Act: -0.1700
Data Index: 7433930 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.2190. Min Act: -0.1700
Data Index: 3191773 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.1718. Min Act: -0.1700
Data Index: 3575991 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.1403. Min Act: -0.1700
Data Index: 1032635 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.1561. Min Act: -0.1700
Data Index: 7116632 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.1403. Min Act: -0.1700
Data Index: 2730640 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.1246. Min Act: -0.1700
Data Index: 6489606 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.1246. Min Act: -0.1700
Data Index: 541226 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.1088. Min Act: -0.1700
Data Index: 7329851 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.1088. Min Act: -0.1700
Data Index: 7627865 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.1088. Min Act: -0.1700
Data Index: 8536295 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.0931. Min Act: -0.1700
Data Index: 7184246 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.0931. Min Act: -0.1700
Data Index: 715990 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.0773. Min Act: -0.1700
Data Index: 1030064 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.0773. Min Act: -0.1700
Data Index: 3116038 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2975. Min Range: -3.2975
Max Act: 3.0773. Min Act: -0.1700
Data Index: 4612486 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19