Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2071. Min Range: -5.2071
Max Act: 5.2071. Min Act: -0.1700
Data Index: 4943994 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2071. Min Range: -5.2071
Max Act: 5.2071. Min Act: -0.1700
Data Index: 8545928 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.9884. Min Act: -0.1700
Data Index: 964884 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.9884. Min Act: -0.1700
Data Index: 5614743 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.9571. Min Act: -0.1700
Data Index: 2051534 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.9571. Min Act: -0.1700
Data Index: 4708680 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.9571. Min Act: -0.1700
Data Index: 4754515 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.8946. Min Act: -0.1700
Data Index: 5144491 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.8946. Min Act: -0.1700
Data Index: 5417885 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.8321. Min Act: -0.1700
Data Index: 8037028 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.8009. Min Act: -0.1700
Data Index: 4546462 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.7696. Min Act: -0.1700
Data Index: 6716032 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.7384. Min Act: -0.1700
Data Index: 7396121 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.7384. Min Act: -0.1700
Data Index: 3923021 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.6446. Min Act: -0.1700
Data Index: 1965268 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.7071. Min Act: -0.1700
Data Index: 37980 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.6759. Min Act: -0.1700
Data Index: 2246943 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.6446. Min Act: -0.1700
Data Index: 950048 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.6446. Min Act: -0.1700
Data Index: 3505401 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2071. Min Range: -5.2071
Max Act: 4.6446. Min Act: -0.1700
Data Index: 2841246 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19