Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4937 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.9913. Min Act: -0.1700
Data Index: 8586297 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.9600. Min Act: -0.1700
Data Index: 6895622 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.7568. Min Act: -0.1700
Data Index: 7905011 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.7098. Min Act: -0.1700
Data Index: 7522734 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.6472. Min Act: -0.1700
Data Index: 7483334 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.6629. Min Act: -0.1700
Data Index: 3747431 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.6160. Min Act: -0.1700
Data Index: 4380416 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.6316. Min Act: -0.1700
Data Index: 8752760 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.6160. Min Act: -0.1700
Data Index: 1262233 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.6160. Min Act: -0.1700
Data Index: 8146288 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.6003. Min Act: -0.1700
Data Index: 3172861 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.5846. Min Act: -0.1700
Data Index: 1685796 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.5690. Min Act: -0.1700
Data Index: 3267068 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.5690. Min Act: -0.1700
Data Index: 4325736 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.5533. Min Act: -0.1700
Data Index: 3340294 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.5533. Min Act: -0.1700
Data Index: 1734546 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.5377. Min Act: -0.1700
Data Index: 7354354 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.5377. Min Act: -0.1700
Data Index: 4154456 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.5220. Min Act: -0.1700
Data Index: 7185801 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9913. Min Range: -3.9913
Max Act: 3.5220. Min Act: -0.1700
Data Index: 5501285 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19