Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1547 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0409. Min Range: -4.0409
Max Act: 4.0409. Min Act: -0.1700
Data Index: 873186 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.9471. Min Act: -0.1700
Data Index: 1013112 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.9158. Min Act: -0.1700
Data Index: 7515440 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.9158. Min Act: -0.1700
Data Index: 6336653 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.8689. Min Act: -0.1700
Data Index: 6281983 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.7595. Min Act: -0.1700
Data Index: 1045818 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.7438. Min Act: -0.1700
Data Index: 8543498 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.7282. Min Act: -0.1700
Data Index: 3961331 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.7126. Min Act: -0.1700
Data Index: 2859475 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.7126. Min Act: -0.1700
Data Index: 2493541 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.7126. Min Act: -0.1700
Data Index: 687204 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.6969. Min Act: -0.1700
Data Index: 8736797 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.6969. Min Act: -0.1700
Data Index: 6805025 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.6969. Min Act: -0.1700
Data Index: 8670914 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.6969. Min Act: -0.1700
Data Index: 2588218 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.6969. Min Act: -0.1700
Data Index: 5672465 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.6656. Min Act: -0.1700
Data Index: 7135912 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.6500. Min Act: -0.1700
Data Index: 7581911 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.6813. Min Act: -0.1700
Data Index: 1944317 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0409. Min Range: -4.0409
Max Act: 3.6656. Min Act: -0.1700
Data Index: 3305993 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19