Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2221 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.9786. Min Act: -0.1700
Data Index: 2284622 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.9473. Min Act: -0.1700
Data Index: 3154600 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.8848. Min Act: -0.1700
Data Index: 2176273 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.8535. Min Act: -0.1700
Data Index: 2103444 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.8535. Min Act: -0.1700
Data Index: 4244805 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.8535. Min Act: -0.1700
Data Index: 2303725 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.8535. Min Act: -0.1700
Data Index: 8657155 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.8222. Min Act: -0.1700
Data Index: 7287115 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.8222. Min Act: -0.1700
Data Index: 7282454 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.7597. Min Act: -0.1700
Data Index: 6129012 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.7910. Min Act: -0.1700
Data Index: 4830772 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.7597. Min Act: -0.1700
Data Index: 7916559 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.7910. Min Act: -0.1700
Data Index: 2161182 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.7910. Min Act: -0.1700
Data Index: 7672940 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.7597. Min Act: -0.1700
Data Index: 4825313 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.7910. Min Act: -0.1700
Data Index: 2308121 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.7597. Min Act: -0.1700
Data Index: 684998 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.7910. Min Act: -0.1700
Data Index: 4665118 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.7284. Min Act: -0.1700
Data Index: 3479188 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9786. Min Range: -3.9786
Max Act: 3.7910. Min Act: -0.1700
Data Index: 5953420 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19