Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2536 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0352. Min Range: -5.0352
Max Act: 5.0352. Min Act: -0.1700
Data Index: 1229203 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.9102. Min Act: -0.1700
Data Index: 4005691 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.7227. Min Act: -0.1700
Data Index: 4015825 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.7227. Min Act: -0.1700
Data Index: 6654631 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.6602. Min Act: -0.1700
Data Index: 2962358 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.6290. Min Act: -0.1700
Data Index: 3881803 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5977. Min Act: -0.1700
Data Index: 8280757 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5977. Min Act: -0.1700
Data Index: 1242976 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.6290. Min Act: -0.1700
Data Index: 627553 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.6290. Min Act: -0.1700
Data Index: 6835244 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.6290. Min Act: -0.1700
Data Index: 1332747 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5977. Min Act: -0.1700
Data Index: 7417505 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5977. Min Act: -0.1700
Data Index: 5907263 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5352. Min Act: -0.1700
Data Index: 2813595 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5665. Min Act: -0.1700
Data Index: 3557433 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5665. Min Act: -0.1700
Data Index: 8625371 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5352. Min Act: -0.1700
Data Index: 1332530 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5665. Min Act: -0.1700
Data Index: 4668760 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5352. Min Act: -0.1700
Data Index: 4683323 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0352. Min Range: -5.0352
Max Act: 4.5040. Min Act: -0.1700
Data Index: 3558085 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19