Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3380 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.9345. Min Act: -0.1700
Data Index: 2532413 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.9345. Min Act: -0.1700
Data Index: 6198745 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.8720. Min Act: -0.1700
Data Index: 2728622 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.8408. Min Act: -0.1700
Data Index: 2236810 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.7158. Min Act: -0.1700
Data Index: 5904210 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.6845. Min Act: -0.1700
Data Index: 2613976 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.6845. Min Act: -0.1700
Data Index: 3541458 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.5908. Min Act: -0.1700
Data Index: 7952345 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.5908. Min Act: -0.1700
Data Index: 3397091 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.5595. Min Act: -0.1700
Data Index: 4124772 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.5595. Min Act: -0.1700
Data Index: 4982366 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.5595. Min Act: -0.1700
Data Index: 616515 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.5283. Min Act: -0.1700
Data Index: 5893927 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.5283. Min Act: -0.1700
Data Index: 1910738 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.5283. Min Act: -0.1700
Data Index: 6340169 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.4970. Min Act: -0.1700
Data Index: 4205958 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.5283. Min Act: -0.1700
Data Index: 2099906 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.4970. Min Act: -0.1700
Data Index: 3412349 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.4970. Min Act: -0.1700
Data Index: 4834698 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9345. Min Range: -5.9345
Max Act: 5.4658. Min Act: -0.1700
Data Index: 1623710 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19