Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4903 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2999. Min Range: -6.2999
Max Act: 6.2999. Min Act: -0.1700
Data Index: 6972969 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2999. Min Range: -6.2999
Max Act: 6.2374. Min Act: -0.1700
Data Index: 1932878 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2999. Min Range: -6.2999
Max Act: 6.1124. Min Act: -0.1700
Data Index: 7513548 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2999. Min Range: -6.2999
Max Act: 6.1124. Min Act: -0.1700
Data Index: 5097493 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2999. Min Range: -6.2999
Max Act: 6.1124. Min Act: -0.1700
Data Index: 1797322 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2999. Min Range: -6.2999
Max Act: 6.0499. Min Act: -0.1700
Data Index: 4672008 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2999. Min Range: -6.2999
Max Act: 6.0187. Min Act: -0.1700
Data Index: 2749994 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.9874. Min Act: -0.1700
Data Index: 952981 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.9562. Min Act: -0.1700
Data Index: 5656742 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.8937. Min Act: -0.1700
Data Index: 6274795 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.8937. Min Act: -0.1700
Data Index: 759356 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.8624. Min Act: -0.1700
Data Index: 3331330 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.8312. Min Act: -0.1700
Data Index: 3228953 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.7999. Min Act: -0.1700
Data Index: 5777522 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.7687. Min Act: -0.1700
Data Index: 3440957 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.7687. Min Act: -0.1700
Data Index: 4107049 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.7687. Min Act: -0.1700
Data Index: 1185038 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.7687. Min Act: -0.1700
Data Index: 6748012 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.7687. Min Act: -0.1700
Data Index: 3195397 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2999. Min Range: -6.2999
Max Act: 5.7374. Min Act: -0.1700
Data Index: 2582633 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19