Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 390 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.4921. Min Act: -0.1700
Data Index: 7295641 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.4608. Min Act: -0.1700
Data Index: 6169195 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.3671. Min Act: -0.1700
Data Index: 5712240 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2421. Min Act: -0.1700
Data Index: 876257 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2421. Min Act: -0.1700
Data Index: 644270 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2733. Min Act: -0.1700
Data Index: 3865184 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2421. Min Act: -0.1700
Data Index: 751915 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2108. Min Act: -0.1700
Data Index: 5936831 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2108. Min Act: -0.1700
Data Index: 8305635 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.2108. Min Act: -0.1700
Data Index: 8223676 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.1796. Min Act: -0.1700
Data Index: 7203637 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.1796. Min Act: -0.1700
Data Index: 332644 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.1796. Min Act: -0.1700
Data Index: 7805826 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.1170. Min Act: -0.1700
Data Index: 4259582 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.1170. Min Act: -0.1700
Data Index: 496514 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.0858. Min Act: -0.1700
Data Index: 5927541 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.1170. Min Act: -0.1700
Data Index: 2813638 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.0233. Min Act: -0.1700
Data Index: 2295656 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.1170. Min Act: -0.1700
Data Index: 8072269 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4921. Min Range: -4.4921
Max Act: 4.0233. Min Act: -0.1700
Data Index: 2333610 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19