Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 724 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.7520. Min Act: -0.1700
Data Index: 1045205 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.7207. Min Act: -0.1700
Data Index: 765114 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.6268. Min Act: -0.1700
Data Index: 1778593 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.5955. Min Act: -0.1700
Data Index: 2582762 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.5955. Min Act: -0.1700
Data Index: 4462770 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.5642. Min Act: -0.1700
Data Index: 7660895 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.5642. Min Act: -0.1700
Data Index: 6131982 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.5016. Min Act: -0.1700
Data Index: 1372296 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.5016. Min Act: -0.1700
Data Index: 8388808 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.5016. Min Act: -0.1700
Data Index: 4454855 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.4859. Min Act: -0.1700
Data Index: 2780080 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.4703. Min Act: -0.1700
Data Index: 6815002 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.4389. Min Act: -0.1700
Data Index: 6987138 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.4546. Min Act: -0.1700
Data Index: 4420408 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.4389. Min Act: -0.1700
Data Index: 7800409 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.4546. Min Act: -0.1700
Data Index: 3596179 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.4233. Min Act: -0.1700
Data Index: 4161990 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.4233. Min Act: -0.1700
Data Index: 8139709 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.4076. Min Act: -0.1700
Data Index: 1250272 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7520. Min Range: -3.7520
Max Act: 3.3919. Min Act: -0.1700
Data Index: 690027 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19