Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5476. Min Range: -8.5476
Max Act: 8.5476. Min Act: -0.1700
Data Index: 591210 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5476. Min Range: -8.5476
Max Act: 8.4851. Min Act: -0.1700
Data Index: 6734494 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5476. Min Range: -8.5476
Max Act: 8.3601. Min Act: -0.1700
Data Index: 2272043 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5476. Min Range: -8.5476
Max Act: 8.3601. Min Act: -0.1700
Data Index: 2492287 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5476. Min Range: -8.5476
Max Act: 8.3601. Min Act: -0.1700
Data Index: 591209 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5476. Min Range: -8.5476
Max Act: 8.3601. Min Act: -0.1700
Data Index: 6343755 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5476. Min Range: -8.5476
Max Act: 8.2039. Min Act: -0.1700
Data Index: 1292638 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5476. Min Range: -8.5476
Max Act: 8.0789. Min Act: -0.1700
Data Index: 7839437 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5476. Min Range: -8.5476
Max Act: 8.0789. Min Act: -0.1700
Data Index: 3767110 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5476. Min Range: -8.5476
Max Act: 7.9851. Min Act: -0.1700
Data Index: 139714 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5476. Min Range: -8.5476
Max Act: 7.9851. Min Act: -0.1700
Data Index: 3006412 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5476. Min Range: -8.5476
Max Act: 7.9851. Min Act: -0.1700
Data Index: 2356397 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5476. Min Range: -8.5476
Max Act: 7.9539. Min Act: -0.1700
Data Index: 7620818 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5476. Min Range: -8.5476
Max Act: 7.9226. Min Act: -0.1700
Data Index: 4445660 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5476. Min Range: -8.5476
Max Act: 7.8914. Min Act: -0.1700
Data Index: 4702151 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5476. Min Range: -8.5476
Max Act: 7.9226. Min Act: -0.1700
Data Index: 2961973 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5476. Min Range: -8.5476
Max Act: 7.8914. Min Act: -0.1700
Data Index: 4269677 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5476. Min Range: -8.5476
Max Act: 7.8289. Min Act: -0.1700
Data Index: 388387 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5476. Min Range: -8.5476
Max Act: 7.8289. Min Act: -0.1700
Data Index: 1663184 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5476. Min Range: -8.5476
Max Act: 7.8601. Min Act: -0.1700
Data Index: 1590176 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19