Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.7536. Min Act: -0.1700
Data Index: 1441422 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.7536. Min Act: -0.1700
Data Index: 364328 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.6286. Min Act: -0.1700
Data Index: 7213818 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.3786. Min Act: -0.1700
Data Index: 4046751 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.1911. Min Act: -0.1700
Data Index: 328679 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.1911. Min Act: -0.1700
Data Index: 8495025 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.1911. Min Act: -0.1700
Data Index: 4821073 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.1911. Min Act: -0.1700
Data Index: 749441 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.1911. Min Act: -0.1700
Data Index: 5986931 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.1286. Min Act: -0.1700
Data Index: 3097180 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.1286. Min Act: -0.1700
Data Index: 866795 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.0661. Min Act: -0.1700
Data Index: 8034621 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.0661. Min Act: -0.1700
Data Index: 7909270 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.0661. Min Act: -0.1700
Data Index: 5259853 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.0036. Min Act: -0.1700
Data Index: 6502602 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.0036. Min Act: -0.1700
Data Index: 5983658 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.0661. Min Act: -0.1700
Data Index: 7437141 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.0661. Min Act: -0.1700
Data Index: 1367066 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7536. Min Range: -8.7536
Max Act: 8.0036. Min Act: -0.1700
Data Index: 4130064 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7536. Min Range: -8.7536
Max Act: 7.9411. Min Act: -0.1700
Data Index: 6358701 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19