Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 70 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.6486. Min Act: -0.1700
Data Index: 816571 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.5703. Min Act: -0.1700
Data Index: 3595720 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.5390. Min Act: -0.1700
Data Index: 5975925 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.5390. Min Act: -0.1700
Data Index: 6233348 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.5077. Min Act: -0.1700
Data Index: 3886968 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.5233. Min Act: -0.1700
Data Index: 2981256 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.5233. Min Act: -0.1700
Data Index: 8046318 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4920. Min Act: -0.1700
Data Index: 813942 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4763. Min Act: -0.1700
Data Index: 3560124 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4920. Min Act: -0.1700
Data Index: 7479472 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4763. Min Act: -0.1700
Data Index: 6684503 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4450. Min Act: -0.1700
Data Index: 6620816 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4450. Min Act: -0.1700
Data Index: 5797153 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4450. Min Act: -0.1700
Data Index: 2411373 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4450. Min Act: -0.1700
Data Index: 6195982 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4450. Min Act: -0.1700
Data Index: 188700 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4293. Min Act: -0.1700
Data Index: 2734136 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4293. Min Act: -0.1700
Data Index: 3677338 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4293. Min Act: -0.1700
Data Index: 4707044 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6486. Min Range: -3.6486
Max Act: 3.4293. Min Act: -0.1700
Data Index: 3287829 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19