Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3647 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.8288. Min Act: -0.1700
Data Index: 3469732 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.8288. Min Act: -0.1700
Data Index: 5662878 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.7975. Min Act: -0.1700
Data Index: 2636410 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.7350. Min Act: -0.1700
Data Index: 518810 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.7350. Min Act: -0.1700
Data Index: 3542584 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.7350. Min Act: -0.1700
Data Index: 573982 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.6725. Min Act: -0.1700
Data Index: 1298196 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.6413. Min Act: -0.1700
Data Index: 2902763 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.6413. Min Act: -0.1700
Data Index: 5107539 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.6100. Min Act: -0.1700
Data Index: 5780020 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.6100. Min Act: -0.1700
Data Index: 6891560 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.5475. Min Act: -0.1700
Data Index: 5922842 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.5788. Min Act: -0.1700
Data Index: 5496388 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.5475. Min Act: -0.1700
Data Index: 544447 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.5475. Min Act: -0.1700
Data Index: 2796505 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.6100. Min Act: -0.1700
Data Index: 7312089 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.3913. Min Act: -0.1700
Data Index: 172525 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.5163. Min Act: -0.1700
Data Index: 7738012 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.4850. Min Act: -0.1700
Data Index: 2625723 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8288. Min Range: -6.8288
Max Act: 6.4538. Min Act: -0.1700
Data Index: 159373 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19