Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6353. Min Range: -9.6353
Max Act: 9.6353. Min Act: -0.1700
Data Index: 6235658 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6353. Min Range: -9.6353
Max Act: 9.1978. Min Act: -0.1700
Data Index: 6637890 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6353. Min Range: -9.6353
Max Act: 9.0103. Min Act: -0.1700
Data Index: 4951308 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.8853. Min Act: -0.1700
Data Index: 6928578 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.8228. Min Act: -0.1700
Data Index: 5645860 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.7603. Min Act: -0.1700
Data Index: 2193578 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.7603. Min Act: -0.1700
Data Index: 7519216 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.6978. Min Act: -0.1700
Data Index: 6642362 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.6353. Min Act: -0.1700
Data Index: 3439922 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.6978. Min Act: -0.1700
Data Index: 3780899 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.6978. Min Act: -0.1700
Data Index: 6112686 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.6353. Min Act: -0.1700
Data Index: 2794369 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.5728. Min Act: -0.1700
Data Index: 5920707 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.5728. Min Act: -0.1700
Data Index: 2338730 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.5728. Min Act: -0.1700
Data Index: 5700321 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.5728. Min Act: -0.1700
Data Index: 7345865 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.5728. Min Act: -0.1700
Data Index: 2150966 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.5103. Min Act: -0.1700
Data Index: 8360585 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.5103. Min Act: -0.1700
Data Index: 6505473 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6353. Min Range: -9.6353
Max Act: 8.5728. Min Act: -0.1700
Data Index: 2182864 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19