Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 451 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8408. Min Act: -0.1700
Data Index: 744865 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8567. Min Act: -0.1700
Data Index: 191588 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8408. Min Act: -0.1700
Data Index: 5529782 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8408. Min Act: -0.1700
Data Index: 3203291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8408. Min Act: -0.1700
Data Index: 5475152 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8408. Min Act: -0.1700
Data Index: 1626703 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8408. Min Act: -0.1700
Data Index: 5529785 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8408. Min Act: -0.1700
Data Index: 8635424 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8408. Min Act: -0.1700
Data Index: 5529776 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8249. Min Act: -0.1700
Data Index: 8635407 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8249. Min Act: -0.1700
Data Index: 377578 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8249. Min Act: -0.1700
Data Index: 5529775 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8249. Min Act: -0.1700
Data Index: 6225764 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8249. Min Act: -0.1700
Data Index: 7819641 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8249. Min Act: -0.1700
Data Index: 5529771 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8090. Min Act: -0.1700
Data Index: 2206972 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8090. Min Act: -0.1700
Data Index: 4847872 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8090. Min Act: -0.1700
Data Index: 5529784 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8090. Min Act: -0.1700
Data Index: 5447646 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8567. Min Range: -2.8567
Max Act: 2.8090. Min Act: -0.1700
Data Index: 6940322 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19