Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4555 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.9137. Min Act: -0.1700
Data Index: 2142034 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7938. Min Act: -0.1700
Data Index: 7871800 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7852. Min Act: -0.1700
Data Index: 1976459 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7766. Min Act: -0.1700
Data Index: 4248299 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7680. Min Act: -0.1700
Data Index: 6673780 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7594. Min Act: -0.1700
Data Index: 4311711 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7421. Min Act: -0.1700
Data Index: 918660 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7507. Min Act: -0.1700
Data Index: 183277 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7334. Min Act: -0.1699
Data Index: 3177440 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7334. Min Act: -0.1700
Data Index: 3511201 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7248. Min Act: -0.1700
Data Index: 6956695 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7248. Min Act: -0.1700
Data Index: 8052342 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7161. Min Act: -0.1700
Data Index: 8806809 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7334. Min Act: -0.1700
Data Index: 3205414 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7248. Min Act: -0.1700
Data Index: 67245 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7161. Min Act: -0.1700
Data Index: 2707922 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7161. Min Act: -0.1700
Data Index: 903278 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7161. Min Act: -0.1700
Data Index: 8321326 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7161. Min Act: -0.1700
Data Index: 6574634 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9137. Min Range: -1.9137
Max Act: 1.7075. Min Act: -0.1700
Data Index: 3439887 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19