Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3524 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0138. Min Range: -4.0138
Max Act: 4.0138. Min Act: -0.1700
Data Index: 7595048 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.9825. Min Act: -0.1700
Data Index: 3521039 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.8887. Min Act: -0.1700
Data Index: 1442535 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.9200. Min Act: -0.1700
Data Index: 3079578 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.9200. Min Act: -0.1700
Data Index: 1003239 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.9200. Min Act: -0.1700
Data Index: 1017037 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.8575. Min Act: -0.1700
Data Index: 5926982 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.8262. Min Act: -0.1700
Data Index: 1334407 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.8575. Min Act: -0.1700
Data Index: 6787434 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.9200. Min Act: -0.1700
Data Index: 4820976 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.8575. Min Act: -0.1700
Data Index: 6827540 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.7637. Min Act: -0.1700
Data Index: 8629595 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.7949. Min Act: -0.1700
Data Index: 1897937 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.7637. Min Act: -0.1700
Data Index: 5719335 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.7637. Min Act: -0.1700
Data Index: 1691582 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.7011. Min Act: -0.1700
Data Index: 8453565 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.7324. Min Act: -0.1700
Data Index: 5395148 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.7637. Min Act: -0.1700
Data Index: 2659308 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.7324. Min Act: -0.1700
Data Index: 5270193 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0138. Min Range: -4.0138
Max Act: 3.7324. Min Act: -0.1700
Data Index: 4352957 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19