Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4390 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3406. Min Range: -7.3406
Max Act: 7.3406. Min Act: -0.1700
Data Index: 302512 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3406. Min Range: -7.3406
Max Act: 7.0281. Min Act: -0.1700
Data Index: 2630217 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.9969. Min Act: -0.1700
Data Index: 2329857 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.9656. Min Act: -0.1700
Data Index: 6335354 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.7781. Min Act: -0.1700
Data Index: 7588431 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.7469. Min Act: -0.1700
Data Index: 1157677 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.7781. Min Act: -0.1700
Data Index: 4475078 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.7156. Min Act: -0.1700
Data Index: 2630216 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.7156. Min Act: -0.1700
Data Index: 5138054 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.7156. Min Act: -0.1700
Data Index: 7592036 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.6844. Min Act: -0.1700
Data Index: 2339483 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.7156. Min Act: -0.1700
Data Index: 6115292 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.6531. Min Act: -0.1700
Data Index: 4078898 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.6531. Min Act: -0.1700
Data Index: 3819922 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.5906. Min Act: -0.1700
Data Index: 373469 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.5594. Min Act: -0.1700
Data Index: 6918059 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.5594. Min Act: -0.1700
Data Index: 1509752 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.4969. Min Act: -0.1700
Data Index: 3068033 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.5281. Min Act: -0.1700
Data Index: 2078887 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3406. Min Range: -7.3406
Max Act: 6.5281. Min Act: -0.1700
Data Index: 5747518 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19