Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2406 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.9785. Min Act: -0.1700
Data Index: 527601 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.9472. Min Act: -0.1700
Data Index: 3057036 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.9472. Min Act: -0.1700
Data Index: 6479288 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.9472. Min Act: -0.1700
Data Index: 411416 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8847. Min Act: -0.1700
Data Index: 1513391 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8535. Min Act: -0.1700
Data Index: 6743274 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8847. Min Act: -0.1700
Data Index: 8123984 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8535. Min Act: -0.1700
Data Index: 5603653 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8222. Min Act: -0.1700
Data Index: 1903997 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8535. Min Act: -0.1700
Data Index: 3226993 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8535. Min Act: -0.1700
Data Index: 7192580 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8222. Min Act: -0.1700
Data Index: 7533306 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8222. Min Act: -0.1700
Data Index: 4867697 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.7910. Min Act: -0.1700
Data Index: 2492381 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8222. Min Act: -0.1700
Data Index: 8632253 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8222. Min Act: -0.1700
Data Index: 8525776 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8222. Min Act: -0.1700
Data Index: 3968515 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8222. Min Act: -0.1700
Data Index: 4823304 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.7910. Min Act: -0.1700
Data Index: 6593068 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9785. Min Range: -6.9785
Max Act: 6.8222. Min Act: -0.1700
Data Index: 2670474 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19