Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1136 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.2655. Min Range: -9.2655
Max Act: 9.2655. Min Act: -0.1700
Data Index: 4875720 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.7655. Min Act: -0.1700
Data Index: 330282 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.7655. Min Act: -0.1700
Data Index: 7522345 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.5780. Min Act: -0.1700
Data Index: 3884287 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.4530. Min Act: -0.1700
Data Index: 5188696 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.3905. Min Act: -0.1700
Data Index: 3402654 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.3593. Min Act: -0.1700
Data Index: 1069800 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.3905. Min Act: -0.1700
Data Index: 1207603 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.3593. Min Act: -0.1700
Data Index: 8253582 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.3593. Min Act: -0.1700
Data Index: 5650592 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.3280. Min Act: -0.1700
Data Index: 1880156 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.3593. Min Act: -0.1700
Data Index: 1653179 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.2655. Min Act: -0.1700
Data Index: 442013 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.2343. Min Act: -0.1700
Data Index: 8196675 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.2968. Min Act: -0.1700
Data Index: 5284063 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.2968. Min Act: -0.1700
Data Index: 6499034 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.1718. Min Act: -0.1700
Data Index: 1736483 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.2343. Min Act: -0.1700
Data Index: 7163491 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.1718. Min Act: -0.1700
Data Index: 3539985 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2655. Min Range: -9.2655
Max Act: 8.1093. Min Act: -0.1700
Data Index: 2152503 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19