Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4465 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.8460. Min Act: -0.1700
Data Index: 7662148 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.8148. Min Act: -0.1700
Data Index: 5193446 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.7522. Min Act: -0.1700
Data Index: 7408563 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.7522. Min Act: -0.1700
Data Index: 4438087 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.7209. Min Act: -0.1700
Data Index: 2673354 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6896. Min Act: -0.1700
Data Index: 8721411 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.7209. Min Act: -0.1700
Data Index: 7094854 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6896. Min Act: -0.1700
Data Index: 8030899 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6896. Min Act: -0.1700
Data Index: 6932070 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6896. Min Act: -0.1700
Data Index: 5427978 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6583. Min Act: -0.1700
Data Index: 3052485 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6896. Min Act: -0.1700
Data Index: 3636340 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6583. Min Act: -0.1700
Data Index: 4210011 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6271. Min Act: -0.1700
Data Index: 6157588 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6583. Min Act: -0.1700
Data Index: 123612 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6583. Min Act: -0.1700
Data Index: 2337624 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6271. Min Act: -0.1700
Data Index: 7971942 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6271. Min Act: -0.1700
Data Index: 4213088 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6271. Min Act: -0.1700
Data Index: 3296376 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8460. Min Range: -3.8460
Max Act: 3.6271. Min Act: -0.1700
Data Index: 6702533 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19