Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6373 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2257. Min Range: -7.2257
Max Act: 7.2257. Min Act: -0.1700
Data Index: 4620609 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2257. Min Range: -7.2257
Max Act: 7.0070. Min Act: -0.1700
Data Index: 1032526 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.9757. Min Act: -0.1700
Data Index: 7285067 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.9132. Min Act: -0.1700
Data Index: 6710397 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.8820. Min Act: -0.1700
Data Index: 8222687 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.8507. Min Act: -0.1700
Data Index: 1620318 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.8507. Min Act: -0.1700
Data Index: 2008715 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.8195. Min Act: -0.1700
Data Index: 1171657 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.8195. Min Act: -0.1700
Data Index: 1782094 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.8195. Min Act: -0.1700
Data Index: 7942543 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.7882. Min Act: -0.1700
Data Index: 6564627 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.7570. Min Act: -0.1700
Data Index: 6446050 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.7570. Min Act: -0.1700
Data Index: 2163789 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.7257. Min Act: -0.1700
Data Index: 3532397 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.7257. Min Act: -0.1700
Data Index: 8212654 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.6945. Min Act: -0.1700
Data Index: 7620213 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.7257. Min Act: -0.1700
Data Index: 3266613 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.6632. Min Act: -0.1700
Data Index: 5483321 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.6632. Min Act: -0.1700
Data Index: 7313275 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2257. Min Range: -7.2257
Max Act: 6.6945. Min Act: -0.1700
Data Index: 823261 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19