Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6753. Min Range: -6.6753
Max Act: 6.6753. Min Act: -0.1700
Data Index: 1363007 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6753. Min Range: -6.6753
Max Act: 6.2378. Min Act: -0.1700
Data Index: 5660938 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6753. Min Range: -6.6753
Max Act: 6.1128. Min Act: -0.1700
Data Index: 6094894 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6753. Min Range: -6.6753
Max Act: 6.0503. Min Act: -0.1700
Data Index: 8758144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6753. Min Range: -6.6753
Max Act: 6.0191. Min Act: -0.1700
Data Index: 7301928 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6753. Min Range: -6.6753
Max Act: 6.0503. Min Act: -0.1700
Data Index: 2855124 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.9878. Min Act: -0.1700
Data Index: 5771052 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.9566. Min Act: -0.1700
Data Index: 6285126 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.9253. Min Act: -0.1700
Data Index: 8303887 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.9566. Min Act: -0.1700
Data Index: 7978727 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.9253. Min Act: -0.1700
Data Index: 5277491 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.8941. Min Act: -0.1700
Data Index: 4472351 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.8941. Min Act: -0.1700
Data Index: 6316996 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.8316. Min Act: -0.1700
Data Index: 871501 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.8316. Min Act: -0.1700
Data Index: 5935878 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.8316. Min Act: -0.1700
Data Index: 5520324 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.8003. Min Act: -0.1700
Data Index: 8294324 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.7691. Min Act: -0.1700
Data Index: 1361356 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.8003. Min Act: -0.1700
Data Index: 8124727 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6753. Min Range: -6.6753
Max Act: 5.8003. Min Act: -0.1700
Data Index: 7023070 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19