Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 966 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1726. Min Act: -0.1700
Data Index: 5304010 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1726. Min Act: -0.1669
Data Index: 3267837 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1726. Min Act: -0.1700
Data Index: 7554237 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1462. Min Act: -0.1693
Data Index: 781400 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1374. Min Act: -0.1651
Data Index: 1924131 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1286. Min Act: -0.1699
Data Index: 8387027 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1374. Min Act: -0.1575
Data Index: 160594 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1286. Min Act: -0.1579
Data Index: 8617245 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1199. Min Act: -0.1623
Data Index: 4203408 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1111. Min Act: -0.1699
Data Index: 1120942 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1111. Min Act: -0.1700
Data Index: 319536 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1111. Min Act: -0.1640
Data Index: 7908804 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1111. Min Act: -0.1608
Data Index: 8001609 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1023. Min Act: -0.1588
Data Index: 5873300 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1023. Min Act: -0.1698
Data Index: 4313288 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1023. Min Act: -0.1688
Data Index: 8610425 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1023. Min Act: -0.1570
Data Index: 2003917 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1023. Min Act: -0.1683
Data Index: 6071188 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.1023. Min Act: -0.1690
Data Index: 2428369 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1726. Min Range: -1.1726
Max Act: 1.0936. Min Act: -0.1252
Data Index: 7932940 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19