Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1806 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.8184. Min Act: -0.1700
Data Index: 5060978 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.7871. Min Act: -0.1700
Data Index: 7666280 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.7871. Min Act: -0.1700
Data Index: 831759 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.7559. Min Act: -0.1700
Data Index: 4903692 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.7246. Min Act: -0.1700
Data Index: 5187945 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6934. Min Act: -0.1700
Data Index: 7333454 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6309. Min Act: -0.1700
Data Index: 171566 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6621. Min Act: -0.1700
Data Index: 6590012 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6621. Min Act: -0.1700
Data Index: 6464398 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6309. Min Act: -0.1700
Data Index: 345903 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6621. Min Act: -0.1700
Data Index: 5025591 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6621. Min Act: -0.1700
Data Index: 6728855 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6621. Min Act: -0.1700
Data Index: 2141586 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6309. Min Act: -0.1700
Data Index: 4600552 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.5996. Min Act: -0.1700
Data Index: 7226846 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6309. Min Act: -0.1700
Data Index: 5359686 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6309. Min Act: -0.1700
Data Index: 8061216 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.5996. Min Act: -0.1700
Data Index: 4413583 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.6309. Min Act: -0.1700
Data Index: 3107274 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8184. Min Range: -5.8184
Max Act: 5.5996. Min Act: -0.1700
Data Index: 1981290 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19