Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.2979. Min Act: -0.1700
Data Index: 563153 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.2042. Min Act: -0.1700
Data Index: 4850472 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.1417. Min Act: -0.1700
Data Index: 8394277 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.1417. Min Act: -0.1700
Data Index: 7909296 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.1417. Min Act: -0.1700
Data Index: 7624596 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.1417. Min Act: -0.1700
Data Index: 7737447 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.1104. Min Act: -0.1700
Data Index: 5297738 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.1417. Min Act: -0.1700
Data Index: 8648399 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.1417. Min Act: -0.1700
Data Index: 280017 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.1417. Min Act: -0.1700
Data Index: 2446312 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.0792. Min Act: -0.1700
Data Index: 211528 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.0792. Min Act: -0.1700
Data Index: 1538478 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.0792. Min Act: -0.1700
Data Index: 1599800 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.0792. Min Act: -0.1700
Data Index: 722252 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.0479. Min Act: -0.1700
Data Index: 3250018 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.0479. Min Act: -0.1700
Data Index: 1677793 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.0166. Min Act: -0.1700
Data Index: 4850469 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2979. Min Range: -4.2979
Max Act: 4.0479. Min Act: -0.1700
Data Index: 722256 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.9541. Min Act: -0.1700
Data Index: 7734302 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2979. Min Range: -4.2979
Max Act: 3.9854. Min Act: -0.1700
Data Index: 8070174 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19