Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 854 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.7526. Min Act: -0.1700
Data Index: 3690711 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.6589. Min Act: -0.1700
Data Index: 3598231 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.5651. Min Act: -0.1700
Data Index: 1262251 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.5026. Min Act: -0.1700
Data Index: 3308677 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4714. Min Act: -0.1700
Data Index: 949804 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.5026. Min Act: -0.1700
Data Index: 7093470 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.5026. Min Act: -0.1700
Data Index: 1135459 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4714. Min Act: -0.1700
Data Index: 5210477 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4401. Min Act: -0.1700
Data Index: 8100291 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.3776. Min Act: -0.1700
Data Index: 6275610 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4089. Min Act: -0.1700
Data Index: 3830729 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4089. Min Act: -0.1700
Data Index: 5127951 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4089. Min Act: -0.1700
Data Index: 795623 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4089. Min Act: -0.1700
Data Index: 7798398 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4089. Min Act: -0.1700
Data Index: 6629551 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4089. Min Act: -0.1700
Data Index: 4588834 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4089. Min Act: -0.1700
Data Index: 2597956 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4089. Min Act: -0.1700
Data Index: 3893863 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.4089. Min Act: -0.1700
Data Index: 8267744 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7526. Min Range: -4.7526
Max Act: 4.3776. Min Act: -0.1700
Data Index: 3505756 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19