Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 347 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2117. Min Range: -6.2117
Max Act: 6.2117. Min Act: -0.1700
Data Index: 2776592 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2117. Min Range: -6.2117
Max Act: 6.2117. Min Act: -0.1700
Data Index: 3083422 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2117. Min Range: -6.2117
Max Act: 6.1492. Min Act: -0.1700
Data Index: 7958224 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2117. Min Range: -6.2117
Max Act: 6.1492. Min Act: -0.1700
Data Index: 6474510 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2117. Min Range: -6.2117
Max Act: 6.0867. Min Act: -0.1700
Data Index: 6868772 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2117. Min Range: -6.2117
Max Act: 6.0242. Min Act: -0.1700
Data Index: 955347 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.9930. Min Act: -0.1700
Data Index: 6921378 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.9930. Min Act: -0.1700
Data Index: 3093610 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.9930. Min Act: -0.1700
Data Index: 7508168 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.9617. Min Act: -0.1700
Data Index: 7355615 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.9305. Min Act: -0.1700
Data Index: 965746 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.8992. Min Act: -0.1700
Data Index: 6613494 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.8992. Min Act: -0.1700
Data Index: 5342486 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.8992. Min Act: -0.1700
Data Index: 3535754 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.8992. Min Act: -0.1700
Data Index: 5228761 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.8992. Min Act: -0.1700
Data Index: 5786954 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.8992. Min Act: -0.1700
Data Index: 2776590 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.8680. Min Act: -0.1700
Data Index: 4422099 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.8680. Min Act: -0.1700
Data Index: 3547870 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2117. Min Range: -6.2117
Max Act: 5.8680. Min Act: -0.1700
Data Index: 866375 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19