Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2019 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.4967. Min Act: -0.1700
Data Index: 3644719 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.3717. Min Act: -0.1700
Data Index: 3159821 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.3717. Min Act: -0.1700
Data Index: 8324267 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.3092. Min Act: -0.1700
Data Index: 2459306 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.3092. Min Act: -0.1700
Data Index: 8364930 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.3092. Min Act: -0.1700
Data Index: 1053911 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.2467. Min Act: -0.1700
Data Index: 7558265 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.2467. Min Act: -0.1700
Data Index: 1720665 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.2467. Min Act: -0.1700
Data Index: 7673958 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.1842. Min Act: -0.1700
Data Index: 3124571 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.1842. Min Act: -0.1700
Data Index: 7508142 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.1842. Min Act: -0.1700
Data Index: 1971034 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.1217. Min Act: -0.1700
Data Index: 591239 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.1217. Min Act: -0.1700
Data Index: 6713673 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.1217. Min Act: -0.1700
Data Index: 8251818 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.1217. Min Act: -0.1700
Data Index: 6886709 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.0592. Min Act: -0.1700
Data Index: 5828861 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.0592. Min Act: -0.1700
Data Index: 2521492 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.0592. Min Act: -0.1700
Data Index: 1208263 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4967. Min Range: -8.4967
Max Act: 8.0592. Min Act: -0.1700
Data Index: 5337791 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19