Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3176 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.6344. Min Act: -0.1700
Data Index: 99502 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.5407. Min Act: -0.1700
Data Index: 8519528 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.5094. Min Act: -0.1700
Data Index: 7726889 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.4469. Min Act: -0.1700
Data Index: 7227700 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.4782. Min Act: -0.1700
Data Index: 4423400 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.4782. Min Act: -0.1700
Data Index: 99503 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.4782. Min Act: -0.1700
Data Index: 8385012 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.4157. Min Act: -0.1700
Data Index: 6914465 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.4157. Min Act: -0.1700
Data Index: 8511220 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3844. Min Act: -0.1700
Data Index: 99498 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3532. Min Act: -0.1700
Data Index: 1572711 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3532. Min Act: -0.1700
Data Index: 8385010 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3532. Min Act: -0.1700
Data Index: 3979921 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3532. Min Act: -0.1700
Data Index: 558158 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3532. Min Act: -0.1700
Data Index: 2414208 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3219. Min Act: -0.1700
Data Index: 1759869 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3219. Min Act: -0.1700
Data Index: 2921266 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3219. Min Act: -0.1700
Data Index: 1891424 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.3219. Min Act: -0.1700
Data Index: 99501 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6344. Min Range: -6.6344
Max Act: 6.2907. Min Act: -0.1700
Data Index: 704842 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19