Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.4803. Min Act: -0.1700
Data Index: 8254074 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.3553. Min Act: -0.1700
Data Index: 8294540 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.2928. Min Act: -0.1700
Data Index: 1850297 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.2615. Min Act: -0.1700
Data Index: 7712206 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.1990. Min Act: -0.1700
Data Index: 2295579 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.1365. Min Act: -0.1700
Data Index: 3977442 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.1053. Min Act: -0.1700
Data Index: 2517050 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.1053. Min Act: -0.1700
Data Index: 5529373 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.0740. Min Act: -0.1700
Data Index: 7341117 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.0428. Min Act: -0.1700
Data Index: 2173703 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.0115. Min Act: -0.1700
Data Index: 1932952 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.0428. Min Act: -0.1700
Data Index: 7507300 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.0115. Min Act: -0.1700
Data Index: 200982 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4803. Min Range: -6.4803
Max Act: 6.0115. Min Act: -0.1700
Data Index: 4168369 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4803. Min Range: -6.4803
Max Act: 5.9803. Min Act: -0.1700
Data Index: 8815767 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4803. Min Range: -6.4803
Max Act: 5.9803. Min Act: -0.1700
Data Index: 3326735 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4803. Min Range: -6.4803
Max Act: 5.9490. Min Act: -0.1700
Data Index: 7014854 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4803. Min Range: -6.4803
Max Act: 5.9490. Min Act: -0.1700
Data Index: 571754 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4803. Min Range: -6.4803
Max Act: 5.9490. Min Act: -0.1700
Data Index: 8085980 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4803. Min Range: -6.4803
Max Act: 5.9490. Min Act: -0.1700
Data Index: 7481205 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19