Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2666 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.4271. Min Act: -0.1700
Data Index: 401065 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.3959. Min Act: -0.1700
Data Index: 5980606 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.3959. Min Act: -0.1700
Data Index: 7982821 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.3646. Min Act: -0.1700
Data Index: 8320624 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.1146. Min Act: -0.1700
Data Index: 3773548 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.0834. Min Act: -0.1700
Data Index: 2869682 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.0521. Min Act: -0.1700
Data Index: 2533224 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4271. Min Range: -6.4271
Max Act: 6.0521. Min Act: -0.1700
Data Index: 1627610 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.9896. Min Act: -0.1700
Data Index: 7045014 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.9271. Min Act: -0.1700
Data Index: 2905110 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.9271. Min Act: -0.1700
Data Index: 1077924 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.8959. Min Act: -0.1700
Data Index: 7870937 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.8959. Min Act: -0.1700
Data Index: 5826073 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.8959. Min Act: -0.1700
Data Index: 774025 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.8334. Min Act: -0.1700
Data Index: 429305 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.8646. Min Act: -0.1700
Data Index: 4193132 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.8334. Min Act: -0.1700
Data Index: 867042 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.8334. Min Act: -0.1700
Data Index: 19360 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.8021. Min Act: -0.1700
Data Index: 5232284 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4271. Min Range: -6.4271
Max Act: 5.8021. Min Act: -0.1700
Data Index: 21233 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19