Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3540 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1997. Min Range: -8.1997
Max Act: 8.1997. Min Act: -0.1700
Data Index: 1632615 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1997. Min Range: -8.1997
Max Act: 8.0747. Min Act: -0.1700
Data Index: 2297298 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.7622. Min Act: -0.1700
Data Index: 182556 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.6997. Min Act: -0.1700
Data Index: 3556695 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.6997. Min Act: -0.1700
Data Index: 4930772 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.6997. Min Act: -0.1700
Data Index: 662389 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.6997. Min Act: -0.1700
Data Index: 2256532 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.6372. Min Act: -0.1700
Data Index: 1837490 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.6372. Min Act: -0.1700
Data Index: 8600047 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.6372. Min Act: -0.1700
Data Index: 6277505 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.5435. Min Act: -0.1700
Data Index: 8775317 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.5747. Min Act: -0.1700
Data Index: 5922355 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.5122. Min Act: -0.1700
Data Index: 5767402 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.5435. Min Act: -0.1700
Data Index: 246773 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.5122. Min Act: -0.1700
Data Index: 8228742 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.4497. Min Act: -0.1700
Data Index: 2602668 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.3872. Min Act: -0.1700
Data Index: 5909207 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.3872. Min Act: -0.1700
Data Index: 3787307 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.3560. Min Act: -0.1700
Data Index: 2877882 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1997. Min Range: -8.1997
Max Act: 7.3560. Min Act: -0.1700
Data Index: 3936450 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19