Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.5331. Min Act: -0.1700
Data Index: 6292726 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.2518. Min Act: -0.1700
Data Index: 459683 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.2518. Min Act: -0.1700
Data Index: 26894 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.2206. Min Act: -0.1700
Data Index: 3715552 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.1581. Min Act: -0.1700
Data Index: 1315179 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.1581. Min Act: -0.1700
Data Index: 622162 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.1268. Min Act: -0.1700
Data Index: 2985427 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.0643. Min Act: -0.1700
Data Index: 1035913 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.0643. Min Act: -0.1700
Data Index: 7339166 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.0331. Min Act: -0.1700
Data Index: 3288450 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.0331. Min Act: -0.1700
Data Index: 3959536 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.0018. Min Act: -0.1700
Data Index: 8701921 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.0018. Min Act: -0.1700
Data Index: 578947 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.0018. Min Act: -0.1700
Data Index: 4111140 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.0018. Min Act: -0.1700
Data Index: 8090846 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5331. Min Range: -7.5331
Max Act: 7.0018. Min Act: -0.1700
Data Index: 1701732 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5331. Min Range: -7.5331
Max Act: 6.9706. Min Act: -0.1700
Data Index: 3851899 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5331. Min Range: -7.5331
Max Act: 6.9706. Min Act: -0.1700
Data Index: 1094200 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5331. Min Range: -7.5331
Max Act: 6.9393. Min Act: -0.1700
Data Index: 8557407 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5331. Min Range: -7.5331
Max Act: 6.9393. Min Act: -0.1700
Data Index: 4321679 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19