Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1280. Min Range: -4.1280
Max Act: 4.1280. Min Act: -0.1700
Data Index: 3528121 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1280. Min Range: -4.1280
Max Act: 4.0655. Min Act: -0.1700
Data Index: 1332136 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.9405. Min Act: -0.1700
Data Index: 5544248 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.8154. Min Act: -0.1700
Data Index: 1423988 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.7685. Min Act: -0.1700
Data Index: 6675210 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.7529. Min Act: -0.1700
Data Index: 4699650 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.7372. Min Act: -0.1700
Data Index: 312177 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.7216. Min Act: -0.1700
Data Index: 2884364 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.7216. Min Act: -0.1700
Data Index: 2037840 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.7372. Min Act: -0.1700
Data Index: 4045340 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.6746. Min Act: -0.1700
Data Index: 8134597 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.6590. Min Act: -0.1700
Data Index: 1871202 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.5964. Min Act: -0.1700
Data Index: 53716 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.6277. Min Act: -0.1700
Data Index: 4997454 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.6277. Min Act: -0.1700
Data Index: 6019655 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.6277. Min Act: -0.1700
Data Index: 7864309 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.6121. Min Act: -0.1700
Data Index: 108351 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.6121. Min Act: -0.1700
Data Index: 4855549 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.5964. Min Act: -0.1700
Data Index: 5398667 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1280. Min Range: -4.1280
Max Act: 3.5964. Min Act: -0.1700
Data Index: 6952735 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19