Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3768 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2128. Min Range: -5.2128
Max Act: 5.2128. Min Act: -0.1700
Data Index: 6808460 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2128. Min Range: -5.2128
Max Act: 5.0253. Min Act: -0.1700
Data Index: 2559264 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8690. Min Act: -0.1700
Data Index: 6685052 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8065. Min Act: -0.1700
Data Index: 2390889 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8065. Min Act: -0.1700
Data Index: 559073 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8378. Min Act: -0.1700
Data Index: 2453261 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.8065. Min Act: -0.1700
Data Index: 3434322 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.7440. Min Act: -0.1700
Data Index: 2873478 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.7753. Min Act: -0.1700
Data Index: 4287927 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.7440. Min Act: -0.1700
Data Index: 2896524 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.7440. Min Act: -0.1700
Data Index: 1481388 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.7440. Min Act: -0.1700
Data Index: 3434335 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.7440. Min Act: -0.1700
Data Index: 4021774 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.6815. Min Act: -0.1700
Data Index: 1243057 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.7440. Min Act: -0.1700
Data Index: 5747531 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.7128. Min Act: -0.1700
Data Index: 5747539 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.7440. Min Act: -0.1700
Data Index: 151064 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.6815. Min Act: -0.1700
Data Index: 4196246 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.6503. Min Act: -0.1700
Data Index: 5098984 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2128. Min Range: -5.2128
Max Act: 4.6190. Min Act: -0.1700
Data Index: 3755302 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19