Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 512 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.8240. Min Act: -0.1700
Data Index: 4712182 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7982. Min Act: -0.1700
Data Index: 6458889 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7810. Min Act: -0.1700
Data Index: 8466471 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7724. Min Act: -0.1698
Data Index: 5468772 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7638. Min Act: -0.1700
Data Index: 6519633 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7551. Min Act: -0.1700
Data Index: 1786292 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7551. Min Act: -0.1700
Data Index: 3289020 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7551. Min Act: -0.1700
Data Index: 7977032 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7638. Min Act: -0.1700
Data Index: 3533530 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7465. Min Act: -0.1699
Data Index: 3580912 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7465. Min Act: -0.1700
Data Index: 7523309 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7551. Min Act: -0.1700
Data Index: 5792742 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7292. Min Act: -0.1700
Data Index: 5988548 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7119. Min Act: -0.1700
Data Index: 44996 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7119. Min Act: -0.1700
Data Index: 7711777 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7292. Min Act: -0.1700
Data Index: 5862703 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7292. Min Act: -0.1700
Data Index: 4715379 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7205. Min Act: -0.1700
Data Index: 2030976 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7205. Min Act: -0.1700
Data Index: 5136811 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8240. Min Range: -1.8240
Max Act: 1.7205. Min Act: -0.1700
Data Index: 7133403 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19