Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4312. Min Range: -9.4312
Max Act: 9.4312. Min Act: -0.1700
Data Index: 567439 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4312. Min Range: -9.4312
Max Act: 9.1187. Min Act: -0.1700
Data Index: 1629896 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.9937. Min Act: -0.1700
Data Index: 4726775 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.8687. Min Act: -0.1700
Data Index: 5674871 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.9312. Min Act: -0.1700
Data Index: 4160734 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.8687. Min Act: -0.1700
Data Index: 6537957 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.8062. Min Act: -0.1700
Data Index: 3504231 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.7437. Min Act: -0.1700
Data Index: 1994661 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.7437. Min Act: -0.1700
Data Index: 8067709 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.7437. Min Act: -0.1700
Data Index: 559112 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.6812. Min Act: -0.1700
Data Index: 4194216 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.6187. Min Act: -0.1700
Data Index: 7465662 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.5562. Min Act: -0.1700
Data Index: 244818 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.5562. Min Act: -0.1700
Data Index: 5497287 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.4937. Min Act: -0.1700
Data Index: 6857363 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.4312. Min Act: -0.1700
Data Index: 3489344 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.4937. Min Act: -0.1700
Data Index: 1047367 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.4937. Min Act: -0.1700
Data Index: 3870856 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.3687. Min Act: -0.1700
Data Index: 6117165 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4312. Min Range: -9.4312
Max Act: 8.3687. Min Act: -0.1700
Data Index: 4272726 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19