Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2651 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.6697. Min Act: -0.1700
Data Index: 8175317 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.5760. Min Act: -0.1700
Data Index: 223861 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.5447. Min Act: -0.1700
Data Index: 1126835 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.4822. Min Act: -0.1700
Data Index: 3472562 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.4510. Min Act: -0.1700
Data Index: 6728336 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.3572. Min Act: -0.1700
Data Index: 1796370 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.3885. Min Act: -0.1700
Data Index: 3360826 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.3885. Min Act: -0.1700
Data Index: 7922678 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.3572. Min Act: -0.1700
Data Index: 6728337 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.3572. Min Act: -0.1700
Data Index: 5547423 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.3885. Min Act: -0.1700
Data Index: 7490190 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.2947. Min Act: -0.1700
Data Index: 8439844 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.3260. Min Act: -0.1700
Data Index: 1301933 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.2947. Min Act: -0.1700
Data Index: 5484215 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.3260. Min Act: -0.1700
Data Index: 838802 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.2947. Min Act: -0.1700
Data Index: 5914140 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.2947. Min Act: -0.1700
Data Index: 4856733 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.2947. Min Act: -0.1700
Data Index: 382099 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.2947. Min Act: -0.1700
Data Index: 5397644 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6697. Min Range: -4.6697
Max Act: 4.3260. Min Act: -0.1700
Data Index: 2878882 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19