Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.7586. Min Act: -0.1700
Data Index: 5766467 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.6648. Min Act: -0.1700
Data Index: 2918186 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.6335. Min Act: -0.1700
Data Index: 2945720 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.5396. Min Act: -0.1700
Data Index: 3493245 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.5082. Min Act: -0.1700
Data Index: 3137661 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.5239. Min Act: -0.1700
Data Index: 4757529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.5082. Min Act: -0.1700
Data Index: 2826286 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.4612. Min Act: -0.1700
Data Index: 3037172 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.4299. Min Act: -0.1700
Data Index: 6046422 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.4456. Min Act: -0.1700
Data Index: 3299894 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.4299. Min Act: -0.1700
Data Index: 1395917 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.4142. Min Act: -0.1700
Data Index: 198438 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.4142. Min Act: -0.1700
Data Index: 1970431 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.4142. Min Act: -0.1700
Data Index: 6977778 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.4142. Min Act: -0.1700
Data Index: 5251517 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.4299. Min Act: -0.1700
Data Index: 1678905 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.3986. Min Act: -0.1700
Data Index: 5285035 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.4142. Min Act: -0.1700
Data Index: 8551361 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.4142. Min Act: -0.1700
Data Index: 7605050 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7586. Min Range: -3.7586
Max Act: 3.3986. Min Act: -0.1700
Data Index: 7515618 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19