Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5765 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1283. Min Range: -7.1283
Max Act: 7.1283. Min Act: -0.1700
Data Index: 3612563 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1283. Min Range: -7.1283
Max Act: 7.0345. Min Act: -0.1700
Data Index: 1646133 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.8783. Min Act: -0.1700
Data Index: 3997173 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.8470. Min Act: -0.1700
Data Index: 3664852 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.8470. Min Act: -0.1700
Data Index: 3372167 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.7845. Min Act: -0.1700
Data Index: 1278005 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.7845. Min Act: -0.1700
Data Index: 5888270 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.7845. Min Act: -0.1700
Data Index: 1029465 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.7533. Min Act: -0.1700
Data Index: 1734876 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.7220. Min Act: -0.1700
Data Index: 8449820 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.7220. Min Act: -0.1700
Data Index: 2236566 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.7220. Min Act: -0.1700
Data Index: 1911032 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.6908. Min Act: -0.1700
Data Index: 1822592 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.6908. Min Act: -0.1700
Data Index: 2703178 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.6283. Min Act: -0.1700
Data Index: 3108544 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.6595. Min Act: -0.1700
Data Index: 3452906 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.6595. Min Act: -0.1700
Data Index: 6251099 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.6283. Min Act: -0.1700
Data Index: 4567374 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.6283. Min Act: -0.1700
Data Index: 3056270 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1283. Min Range: -7.1283
Max Act: 6.5970. Min Act: -0.1700
Data Index: 2738583 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19