Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0915. Min Range: -8.0915
Max Act: 8.0915. Min Act: -0.1700
Data Index: 7650577 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.7790. Min Act: -0.1700
Data Index: 4788623 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.7165. Min Act: -0.1700
Data Index: 6146546 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.6540. Min Act: -0.1700
Data Index: 6932398 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.5915. Min Act: -0.1700
Data Index: 544409 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.4978. Min Act: -0.1700
Data Index: 8000564 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.4665. Min Act: -0.1700
Data Index: 912329 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.4665. Min Act: -0.1700
Data Index: 2183580 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.4665. Min Act: -0.1700
Data Index: 3997634 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.4353. Min Act: -0.1700
Data Index: 5142579 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.4040. Min Act: -0.1700
Data Index: 7687715 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.4040. Min Act: -0.1700
Data Index: 1985320 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.4040. Min Act: -0.1700
Data Index: 8000565 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.3415. Min Act: -0.1700
Data Index: 8685430 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.3103. Min Act: -0.1700
Data Index: 5380813 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.3103. Min Act: -0.1700
Data Index: 5570308 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.2790. Min Act: -0.1700
Data Index: 8044162 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.2790. Min Act: -0.1700
Data Index: 1390545 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.2165. Min Act: -0.1700
Data Index: 2928496 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0915. Min Range: -8.0915
Max Act: 7.2478. Min Act: -0.1700
Data Index: 4697239 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19