Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1718 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8102. Min Range: -5.8102
Max Act: 5.8102. Min Act: -0.1700
Data Index: 5043815 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8102. Min Range: -5.8102
Max Act: 5.3102. Min Act: -0.1700
Data Index: 4882897 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8102. Min Range: -5.8102
Max Act: 5.2789. Min Act: -0.1700
Data Index: 6345490 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8102. Min Range: -5.8102
Max Act: 5.2164. Min Act: -0.1700
Data Index: 4718491 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8102. Min Range: -5.8102
Max Act: 5.2477. Min Act: -0.1700
Data Index: 1598911 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8102. Min Range: -5.8102
Max Act: 5.1227. Min Act: -0.1700
Data Index: 253467 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8102. Min Range: -5.8102
Max Act: 5.0914. Min Act: -0.1700
Data Index: 6241549 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8102. Min Range: -5.8102
Max Act: 5.0602. Min Act: -0.1700
Data Index: 5945051 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8102. Min Range: -5.8102
Max Act: 5.0289. Min Act: -0.1700
Data Index: 5049429 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8102. Min Range: -5.8102
Max Act: 5.0289. Min Act: -0.1700
Data Index: 1554428 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8102. Min Range: -5.8102
Max Act: 4.9977. Min Act: -0.1700
Data Index: 8779764 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8102. Min Range: -5.8102
Max Act: 4.9664. Min Act: -0.1700
Data Index: 2684197 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8102. Min Range: -5.8102
Max Act: 4.9977. Min Act: -0.1700
Data Index: 2162109 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8102. Min Range: -5.8102
Max Act: 5.0289. Min Act: -0.1700
Data Index: 661964 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8102. Min Range: -5.8102
Max Act: 4.9977. Min Act: -0.1700
Data Index: 3383508 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8102. Min Range: -5.8102
Max Act: 4.9664. Min Act: -0.1700
Data Index: 6973431 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8102. Min Range: -5.8102
Max Act: 4.9664. Min Act: -0.1700
Data Index: 8511617 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8102. Min Range: -5.8102
Max Act: 4.9664. Min Act: -0.1700
Data Index: 4636873 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8102. Min Range: -5.8102
Max Act: 4.9664. Min Act: -0.1700
Data Index: 8075284 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8102. Min Range: -5.8102
Max Act: 4.9039. Min Act: -0.1700
Data Index: 7836223 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19