Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0297. Min Range: -6.0297
Max Act: 6.0297. Min Act: -0.1700
Data Index: 4032807 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.7797. Min Act: -0.1700
Data Index: 1984276 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.7172. Min Act: -0.1700
Data Index: 8105708 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.6547. Min Act: -0.1700
Data Index: 2574508 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.6235. Min Act: -0.1700
Data Index: 3268001 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.5610. Min Act: -0.1700
Data Index: 7539973 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.5610. Min Act: -0.1700
Data Index: 3831499 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.5297. Min Act: -0.1700
Data Index: 7177593 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.5297. Min Act: -0.1700
Data Index: 856178 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.5297. Min Act: -0.1700
Data Index: 8320611 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4985. Min Act: -0.1700
Data Index: 7930341 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.5297. Min Act: -0.1700
Data Index: 3808506 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.5297. Min Act: -0.1700
Data Index: 7238841 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4985. Min Act: -0.1700
Data Index: 15182 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4360. Min Act: -0.1700
Data Index: 7559312 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4672. Min Act: -0.1700
Data Index: 1980557 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4360. Min Act: -0.1700
Data Index: 8320613 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4047. Min Act: -0.1700
Data Index: 3537306 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.4047. Min Act: -0.1700
Data Index: 15183 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0297. Min Range: -6.0297
Max Act: 5.3735. Min Act: -0.1700
Data Index: 3956378 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19