Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2100 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1738. Min Range: -6.1738
Max Act: 6.1738. Min Act: -0.1700
Data Index: 1600236 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1738. Min Range: -6.1738
Max Act: 6.0800. Min Act: -0.1700
Data Index: 3891064 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.9863. Min Act: -0.1700
Data Index: 8767633 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.9863. Min Act: -0.1700
Data Index: 4744886 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1738. Min Range: -6.1738
Max Act: 6.0175. Min Act: -0.1700
Data Index: 3743535 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1738. Min Range: -6.1738
Max Act: 6.0175. Min Act: -0.1700
Data Index: 3239240 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.9863. Min Act: -0.1700
Data Index: 2407655 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.9238. Min Act: -0.1700
Data Index: 5025304 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.9238. Min Act: -0.1700
Data Index: 2440959 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.8925. Min Act: -0.1700
Data Index: 6636553 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.8613. Min Act: -0.1700
Data Index: 8637947 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.8613. Min Act: -0.1700
Data Index: 3067437 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.8613. Min Act: -0.1700
Data Index: 173087 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.8300. Min Act: -0.1700
Data Index: 7398252 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.8613. Min Act: -0.1700
Data Index: 5381563 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.8300. Min Act: -0.1700
Data Index: 8064055 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.7675. Min Act: -0.1700
Data Index: 1396544 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.7988. Min Act: -0.1700
Data Index: 3629191 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.7363. Min Act: -0.1700
Data Index: 7122190 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1738. Min Range: -6.1738
Max Act: 5.7675. Min Act: -0.1700
Data Index: 6048041 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19