Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2382 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.3412. Min Act: -0.1700
Data Index: 5109692 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.1849. Min Act: -0.1700
Data Index: 6321157 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.1536. Min Act: -0.1700
Data Index: 967121 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.1536. Min Act: -0.1700
Data Index: 6608653 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.1224. Min Act: -0.1700
Data Index: 7543312 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.0599. Min Act: -0.1700
Data Index: 10378 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.1224. Min Act: -0.1700
Data Index: 1420021 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.0286. Min Act: -0.1700
Data Index: 8017948 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.0599. Min Act: -0.1700
Data Index: 327918 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.0599. Min Act: -0.1700
Data Index: 2048391 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.0599. Min Act: -0.1700
Data Index: 5899280 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.0599. Min Act: -0.1700
Data Index: 4182175 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.0286. Min Act: -0.1700
Data Index: 2722584 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.0286. Min Act: -0.1700
Data Index: 920927 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.0286. Min Act: -0.1700
Data Index: 856593 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3412. Min Range: -4.3412
Max Act: 4.0286. Min Act: -0.1700
Data Index: 6524599 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3412. Min Range: -4.3412
Max Act: 3.9973. Min Act: -0.1700
Data Index: 1211381 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3412. Min Range: -4.3412
Max Act: 3.9973. Min Act: -0.1700
Data Index: 4252423 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3412. Min Range: -4.3412
Max Act: 3.9661. Min Act: -0.1700
Data Index: 91031 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3412. Min Range: -4.3412
Max Act: 3.9973. Min Act: -0.1700
Data Index: 7725679 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19