Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 355 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1281. Min Range: -5.1281
Max Act: 5.1281. Min Act: -0.1700
Data Index: 4284977 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.9719. Min Act: -0.1700
Data Index: 5858927 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.9406. Min Act: -0.1700
Data Index: 4767930 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.8781. Min Act: -0.1700
Data Index: 8423125 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.8156. Min Act: -0.1700
Data Index: 5528911 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.8156. Min Act: -0.1700
Data Index: 4365783 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7531. Min Act: -0.1700
Data Index: 1511035 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7844. Min Act: -0.1700
Data Index: 5594149 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7531. Min Act: -0.1700
Data Index: 76559 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7531. Min Act: -0.1700
Data Index: 7643649 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7531. Min Act: -0.1700
Data Index: 8726096 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7844. Min Act: -0.1700
Data Index: 2810717 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7531. Min Act: -0.1700
Data Index: 8755524 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7531. Min Act: -0.1700
Data Index: 8283773 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7219. Min Act: -0.1700
Data Index: 8119931 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7219. Min Act: -0.1700
Data Index: 4254148 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.7219. Min Act: -0.1700
Data Index: 8045503 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.6906. Min Act: -0.1700
Data Index: 2389960 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.6906. Min Act: -0.1700
Data Index: 6156262 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1281. Min Range: -5.1281
Max Act: 4.6906. Min Act: -0.1700
Data Index: 4849115 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19