Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.5535. Min Act: -0.1700
Data Index: 8415510 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.4597. Min Act: -0.1700
Data Index: 5302035 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.4597. Min Act: -0.1700
Data Index: 5091306 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.4597. Min Act: -0.1700
Data Index: 2562102 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.4285. Min Act: -0.1700
Data Index: 4859190 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3660. Min Act: -0.1700
Data Index: 6780317 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3660. Min Act: -0.1700
Data Index: 5242052 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3660. Min Act: -0.1700
Data Index: 5015757 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3660. Min Act: -0.1700
Data Index: 738797 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3347. Min Act: -0.1700
Data Index: 2576156 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3347. Min Act: -0.1700
Data Index: 8434665 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3347. Min Act: -0.1700
Data Index: 3275236 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3347. Min Act: -0.1700
Data Index: 2479940 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3660. Min Act: -0.1700
Data Index: 6039711 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3035. Min Act: -0.1700
Data Index: 6910021 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.2722. Min Act: -0.1700
Data Index: 1418163 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3035. Min Act: -0.1700
Data Index: 2971636 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.3035. Min Act: -0.1700
Data Index: 8034524 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.2722. Min Act: -0.1700
Data Index: 7709461 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5535. Min Range: -6.5535
Max Act: 6.2722. Min Act: -0.1700
Data Index: 4883379 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19