Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0191. Min Range: -7.0191
Max Act: 7.0191. Min Act: -0.1700
Data Index: 8162888 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.7691. Min Act: -0.1700
Data Index: 5665751 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.7691. Min Act: -0.1700
Data Index: 7935797 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.7378. Min Act: -0.1700
Data Index: 6380535 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.7691. Min Act: -0.1700
Data Index: 8124584 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.7378. Min Act: -0.1700
Data Index: 7237296 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.6753. Min Act: -0.1700
Data Index: 2580029 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.6128. Min Act: -0.1700
Data Index: 2754840 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.6128. Min Act: -0.1700
Data Index: 4963936 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.5816. Min Act: -0.1700
Data Index: 1981246 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.5503. Min Act: -0.1700
Data Index: 6313625 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.5503. Min Act: -0.1700
Data Index: 3667424 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.5191. Min Act: -0.1700
Data Index: 1154753 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.5191. Min Act: -0.1700
Data Index: 714521 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.5191. Min Act: -0.1700
Data Index: 4873008 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.4566. Min Act: -0.1700
Data Index: 2940534 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.4878. Min Act: -0.1700
Data Index: 8474825 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.4566. Min Act: -0.1700
Data Index: 2741697 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.4566. Min Act: -0.1700
Data Index: 8187234 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0191. Min Range: -7.0191
Max Act: 6.4253. Min Act: -0.1700
Data Index: 5045971 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19