Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1192 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1663. Min Range: -3.1663
Max Act: 3.1663. Min Act: -0.1700
Data Index: 2969486 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1663. Min Range: -3.1663
Max Act: 3.0245. Min Act: -0.1700
Data Index: 2487867 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.9771. Min Act: -0.1700
Data Index: 3456433 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.9296. Min Act: -0.1700
Data Index: 1931683 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8820. Min Act: -0.1700
Data Index: 19655 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.9296. Min Act: -0.1700
Data Index: 4359916 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.9137. Min Act: -0.1700
Data Index: 899526 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8979. Min Act: -0.1700
Data Index: 5621884 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8820. Min Act: -0.1700
Data Index: 6995453 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8820. Min Act: -0.1700
Data Index: 7445879 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8502. Min Act: -0.1700
Data Index: 306550 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8502. Min Act: -0.1700
Data Index: 4347753 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8344. Min Act: -0.1700
Data Index: 4921630 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8344. Min Act: -0.1700
Data Index: 6473715 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8184. Min Act: -0.1700
Data Index: 1810435 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8025. Min Act: -0.1700
Data Index: 5756400 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8025. Min Act: -0.1700
Data Index: 6134424 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8344. Min Act: -0.1700
Data Index: 1690375 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.8184. Min Act: -0.1700
Data Index: 4233953 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1663. Min Range: -3.1663
Max Act: 2.7707. Min Act: -0.1700
Data Index: 2329740 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19