Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0872. Min Range: -7.0872
Max Act: 7.0872. Min Act: -0.1700
Data Index: 6774858 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0872. Min Range: -7.0872
Max Act: 7.0872. Min Act: -0.1700
Data Index: 6774855 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0872. Min Range: -7.0872
Max Act: 7.0560. Min Act: -0.1700
Data Index: 122751 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0872. Min Range: -7.0872
Max Act: 7.0560. Min Act: -0.1700
Data Index: 563774 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0872. Min Range: -7.0872
Max Act: 7.0247. Min Act: -0.1700
Data Index: 3884834 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0872. Min Range: -7.0872
Max Act: 7.0247. Min Act: -0.1700
Data Index: 6774856 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0872. Min Range: -7.0872
Max Act: 7.0247. Min Act: -0.1700
Data Index: 2758195 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0872. Min Range: -7.0872
Max Act: 7.0247. Min Act: -0.1700
Data Index: 5851803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.9935. Min Act: -0.1700
Data Index: 3884836 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.9935. Min Act: -0.1700
Data Index: 3884832 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.9935. Min Act: -0.1700
Data Index: 6588752 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.9935. Min Act: -0.1700
Data Index: 6774857 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.9935. Min Act: -0.1700
Data Index: 5607443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.9310. Min Act: -0.1700
Data Index: 563773 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.9310. Min Act: -0.1700
Data Index: 6508781 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.9310. Min Act: -0.1700
Data Index: 4349724 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.9310. Min Act: -0.1700
Data Index: 4136622 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.9310. Min Act: -0.1700
Data Index: 488177 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.8997. Min Act: -0.1700
Data Index: 2050814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0872. Min Range: -7.0872
Max Act: 6.8997. Min Act: -0.1700
Data Index: 1027608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19