Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.8578. Min Act: -0.1700
Data Index: 2141243 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.7483. Min Act: -0.1700
Data Index: 2656586 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6701. Min Act: -0.1700
Data Index: 7174269 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.7170. Min Act: -0.1700
Data Index: 6642253 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.7170. Min Act: -0.1700
Data Index: 40268 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6544. Min Act: -0.1700
Data Index: 5419918 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6701. Min Act: -0.1700
Data Index: 7355356 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6388. Min Act: -0.1700
Data Index: 4985337 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6231. Min Act: -0.1700
Data Index: 2894323 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6075. Min Act: -0.1700
Data Index: 4571271 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6231. Min Act: -0.1700
Data Index: 2695782 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6075. Min Act: -0.1700
Data Index: 1279930 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6388. Min Act: -0.1700
Data Index: 5462053 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6075. Min Act: -0.1700
Data Index: 6968610 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6388. Min Act: -0.1700
Data Index: 7310617 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.5762. Min Act: -0.1700
Data Index: 8267888 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6075. Min Act: -0.1700
Data Index: 6155326 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6231. Min Act: -0.1700
Data Index: 2040189 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.6075. Min Act: -0.1700
Data Index: 4987696 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8578. Min Range: -3.8578
Max Act: 3.5605. Min Act: -0.1700
Data Index: 4634677 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19