Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.6228. Min Act: -0.1700
Data Index: 6046104 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.5915. Min Act: -0.1700
Data Index: 2059327 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.5602. Min Act: -0.1700
Data Index: 52229 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.5602. Min Act: -0.1700
Data Index: 1933505 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.5446. Min Act: -0.1700
Data Index: 1308863 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4976. Min Act: -0.1700
Data Index: 296466 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4976. Min Act: -0.1700
Data Index: 7651957 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4819. Min Act: -0.1700
Data Index: 4646334 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4819. Min Act: -0.1700
Data Index: 3078847 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4819. Min Act: -0.1700
Data Index: 81810 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4819. Min Act: -0.1700
Data Index: 3138633 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4662. Min Act: -0.1700
Data Index: 7064110 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4506. Min Act: -0.1700
Data Index: 5167745 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4349. Min Act: -0.1700
Data Index: 4550290 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4349. Min Act: -0.1700
Data Index: 5672289 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4349. Min Act: -0.1700
Data Index: 7733538 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4192. Min Act: -0.1700
Data Index: 6948620 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4036. Min Act: -0.1700
Data Index: 6584739 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.4036. Min Act: -0.1700
Data Index: 7065581 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6228. Min Range: -3.6228
Max Act: 3.3879. Min Act: -0.1700
Data Index: 2540802 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19