Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3842. Min Range: -8.3842
Max Act: 8.3842. Min Act: -0.1700
Data Index: 2430065 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3842. Min Range: -8.3842
Max Act: 8.3217. Min Act: -0.1700
Data Index: 8132812 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3842. Min Range: -8.3842
Max Act: 8.2592. Min Act: -0.1700
Data Index: 889731 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3842. Min Range: -8.3842
Max Act: 8.2592. Min Act: -0.1700
Data Index: 4943180 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3842. Min Range: -8.3842
Max Act: 8.1967. Min Act: -0.1700
Data Index: 6206096 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3842. Min Range: -8.3842
Max Act: 8.1967. Min Act: -0.1700
Data Index: 1525305 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3842. Min Range: -8.3842
Max Act: 8.0717. Min Act: -0.1700
Data Index: 1372757 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3842. Min Range: -8.3842
Max Act: 8.0092. Min Act: -0.1700
Data Index: 2352347 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3842. Min Range: -8.3842
Max Act: 8.0092. Min Act: -0.1700
Data Index: 4741146 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3842. Min Range: -8.3842
Max Act: 7.9467. Min Act: -0.1700
Data Index: 4540514 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3842. Min Range: -8.3842
Max Act: 7.9467. Min Act: -0.1700
Data Index: 4685013 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3842. Min Range: -8.3842
Max Act: 7.9467. Min Act: -0.1700
Data Index: 4379481 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3842. Min Range: -8.3842
Max Act: 7.9155. Min Act: -0.1700
Data Index: 2682406 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3842. Min Range: -8.3842
Max Act: 7.9155. Min Act: -0.1700
Data Index: 7430894 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3842. Min Range: -8.3842
Max Act: 7.8842. Min Act: -0.1700
Data Index: 4248023 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3842. Min Range: -8.3842
Max Act: 7.8842. Min Act: -0.1700
Data Index: 75975 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3842. Min Range: -8.3842
Max Act: 7.8217. Min Act: -0.1700
Data Index: 2280921 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3842. Min Range: -8.3842
Max Act: 7.8530. Min Act: -0.1700
Data Index: 891342 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3842. Min Range: -8.3842
Max Act: 7.7905. Min Act: -0.1700
Data Index: 5329481 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3842. Min Range: -8.3842
Max Act: 7.8217. Min Act: -0.1700
Data Index: 1944881 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19