Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2405 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.6229. Min Act: -0.1700
Data Index: 707984 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.2166. Min Act: -0.1700
Data Index: 3006378 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.1854. Min Act: -0.1700
Data Index: 3125819 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.2166. Min Act: -0.1700
Data Index: 8525970 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.1854. Min Act: -0.1700
Data Index: 8102376 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.1541. Min Act: -0.1700
Data Index: 6810599 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.1229. Min Act: -0.1700
Data Index: 680043 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.0916. Min Act: -0.1700
Data Index: 1343771 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.0291. Min Act: -0.1700
Data Index: 2721314 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.0291. Min Act: -0.1700
Data Index: 2218685 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.0291. Min Act: -0.1700
Data Index: 3127658 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6229. Min Range: -5.6229
Max Act: 5.0291. Min Act: -0.1700
Data Index: 7068739 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6229. Min Range: -5.6229
Max Act: 4.9979. Min Act: -0.1700
Data Index: 7338103 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6229. Min Range: -5.6229
Max Act: 4.9666. Min Act: -0.1700
Data Index: 7708432 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6229. Min Range: -5.6229
Max Act: 4.9666. Min Act: -0.1700
Data Index: 5269337 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6229. Min Range: -5.6229
Max Act: 4.9979. Min Act: -0.1700
Data Index: 1219041 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6229. Min Range: -5.6229
Max Act: 4.9354. Min Act: -0.1700
Data Index: 2870645 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6229. Min Range: -5.6229
Max Act: 4.9666. Min Act: -0.1700
Data Index: 879812 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6229. Min Range: -5.6229
Max Act: 4.9354. Min Act: -0.1700
Data Index: 6557889 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6229. Min Range: -5.6229
Max Act: 4.9666. Min Act: -0.1700
Data Index: 909466 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19