Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5432 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4323. Min Range: -6.4323
Max Act: 6.4323. Min Act: -0.1700
Data Index: 7510488 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4323. Min Range: -6.4323
Max Act: 6.3385. Min Act: -0.1700
Data Index: 4496606 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4323. Min Range: -6.4323
Max Act: 6.2135. Min Act: -0.1700
Data Index: 6423569 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4323. Min Range: -6.4323
Max Act: 6.1510. Min Act: -0.1700
Data Index: 1298412 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4323. Min Range: -6.4323
Max Act: 6.0573. Min Act: -0.1700
Data Index: 2076353 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4323. Min Range: -6.4323
Max Act: 6.0573. Min Act: -0.1700
Data Index: 5462107 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4323. Min Range: -6.4323
Max Act: 6.0260. Min Act: -0.1700
Data Index: 6846600 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4323. Min Range: -6.4323
Max Act: 6.0260. Min Act: -0.1700
Data Index: 8816257 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.9635. Min Act: -0.1700
Data Index: 7382620 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.9010. Min Act: -0.1700
Data Index: 175888 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.8698. Min Act: -0.1700
Data Index: 8505336 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.8385. Min Act: -0.1700
Data Index: 1279053 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.8698. Min Act: -0.1700
Data Index: 2057675 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.8385. Min Act: -0.1700
Data Index: 3033868 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.8385. Min Act: -0.1700
Data Index: 5509727 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.7760. Min Act: -0.1700
Data Index: 585801 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.8073. Min Act: -0.1700
Data Index: 8656739 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.8073. Min Act: -0.1700
Data Index: 7220434 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.8385. Min Act: -0.1700
Data Index: 6066830 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4323. Min Range: -6.4323
Max Act: 5.7760. Min Act: -0.1700
Data Index: 7618040 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19