Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 412 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.3727. Min Act: -0.1700
Data Index: 8079743 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.3570. Min Act: -0.1700
Data Index: 4042791 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.3257. Min Act: -0.1700
Data Index: 8432029 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.2943. Min Act: -0.1700
Data Index: 611255 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.2629. Min Act: -0.1700
Data Index: 4016947 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.2471. Min Act: -0.1700
Data Index: 4316820 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.2314. Min Act: -0.1700
Data Index: 3719549 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.2000. Min Act: -0.1700
Data Index: 6262609 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.2000. Min Act: -0.1700
Data Index: 2699190 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.2157. Min Act: -0.1700
Data Index: 3097268 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.2000. Min Act: -0.1700
Data Index: 2537488 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.2000. Min Act: -0.1700
Data Index: 4769178 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.1843. Min Act: -0.1700
Data Index: 1993653 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.1843. Min Act: -0.1700
Data Index: 6948532 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.2000. Min Act: -0.1700
Data Index: 604196 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.1685. Min Act: -0.1700
Data Index: 6822925 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.1685. Min Act: -0.1700
Data Index: 2976000 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.1370. Min Act: -0.1700
Data Index: 333960 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.1528. Min Act: -0.1700
Data Index: 1814587 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3727. Min Range: -3.3727
Max Act: 3.1528. Min Act: -0.1700
Data Index: 1032366 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19