Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2631 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.5785. Min Act: -0.1700
Data Index: 3234029 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.5159. Min Act: -0.1700
Data Index: 5209667 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.5159. Min Act: -0.1700
Data Index: 3200861 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.4689. Min Act: -0.1700
Data Index: 5264318 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.4062. Min Act: -0.1700
Data Index: 5105335 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.3592. Min Act: -0.1700
Data Index: 6214483 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.3278. Min Act: -0.1700
Data Index: 3633112 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.3278. Min Act: -0.1700
Data Index: 1618543 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.2807. Min Act: -0.1700
Data Index: 1589443 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.2493. Min Act: -0.1700
Data Index: 647411 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.2650. Min Act: -0.1700
Data Index: 7327831 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.2650. Min Act: -0.1700
Data Index: 7045141 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.2178. Min Act: -0.1700
Data Index: 1101293 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.2178. Min Act: -0.1700
Data Index: 436648 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.2178. Min Act: -0.1700
Data Index: 8126784 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.2493. Min Act: -0.1700
Data Index: 1466180 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.2021. Min Act: -0.1700
Data Index: 4483647 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.2021. Min Act: -0.1700
Data Index: 2765016 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.2021. Min Act: -0.1700
Data Index: 1776693 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5785. Min Range: -3.5785
Max Act: 3.1864. Min Act: -0.1700
Data Index: 5943355 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19