Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3280. Min Range: -7.3280
Max Act: 7.3280. Min Act: -0.1700
Data Index: 1395207 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3280. Min Range: -7.3280
Max Act: 7.2967. Min Act: -0.1700
Data Index: 3814182 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3280. Min Range: -7.3280
Max Act: 7.2655. Min Act: -0.1700
Data Index: 5884932 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3280. Min Range: -7.3280
Max Act: 7.2030. Min Act: -0.1700
Data Index: 1488938 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3280. Min Range: -7.3280
Max Act: 7.1092. Min Act: -0.1700
Data Index: 5511586 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3280. Min Range: -7.3280
Max Act: 7.0467. Min Act: -0.1700
Data Index: 5165452 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.9217. Min Act: -0.1700
Data Index: 6866178 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.9217. Min Act: -0.1700
Data Index: 2487628 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.8592. Min Act: -0.1700
Data Index: 7945121 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.8592. Min Act: -0.1700
Data Index: 3862842 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.8905. Min Act: -0.1700
Data Index: 406129 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.8592. Min Act: -0.1700
Data Index: 7044088 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.8280. Min Act: -0.1700
Data Index: 3616290 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.8280. Min Act: -0.1700
Data Index: 3405638 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.7655. Min Act: -0.1700
Data Index: 3870529 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.7655. Min Act: -0.1700
Data Index: 3851564 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.7655. Min Act: -0.1700
Data Index: 54146 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.7655. Min Act: -0.1700
Data Index: 7955132 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.6717. Min Act: -0.1700
Data Index: 7613399 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3280. Min Range: -7.3280
Max Act: 6.6717. Min Act: -0.1700
Data Index: 1999996 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19