Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.8999. Min Act: -0.1700
Data Index: 7392797 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.6186. Min Act: -0.1700
Data Index: 7429825 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.5874. Min Act: -0.1700
Data Index: 348697 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.4624. Min Act: -0.1700
Data Index: 1205471 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.4311. Min Act: -0.1700
Data Index: 7105433 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.2749. Min Act: -0.1700
Data Index: 4553246 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.2124. Min Act: -0.1700
Data Index: 4925628 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.1811. Min Act: -0.1700
Data Index: 177610 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.1811. Min Act: -0.1700
Data Index: 2955432 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.1811. Min Act: -0.1700
Data Index: 6662047 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.1499. Min Act: -0.1700
Data Index: 6934735 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.1499. Min Act: -0.1700
Data Index: 292071 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.0874. Min Act: -0.1700
Data Index: 7016439 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.0874. Min Act: -0.1700
Data Index: 3005255 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.0874. Min Act: -0.1700
Data Index: 3977222 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.0874. Min Act: -0.1700
Data Index: 791339 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.0874. Min Act: -0.1700
Data Index: 3164500 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.0874. Min Act: -0.1700
Data Index: 4186798 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.0561. Min Act: -0.1700
Data Index: 5439954 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8999. Min Range: -6.8999
Max Act: 6.0561. Min Act: -0.1700
Data Index: 5058117 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19