Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.2207. Min Act: -0.1700
Data Index: 1891962 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.1270. Min Act: -0.1700
Data Index: 6346864 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.1582. Min Act: -0.1700
Data Index: 7055982 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.1582. Min Act: -0.1700
Data Index: 1177375 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.1270. Min Act: -0.1700
Data Index: 2136011 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.1270. Min Act: -0.1700
Data Index: 7055985 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.1270. Min Act: -0.1700
Data Index: 1327218 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0957. Min Act: -0.1699
Data Index: 8039710 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0957. Min Act: -0.1700
Data Index: 4348798 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.1270. Min Act: -0.1700
Data Index: 6235151 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0957. Min Act: -0.1700
Data Index: 1303615 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0645. Min Act: -0.1700
Data Index: 7065801 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0332. Min Act: -0.1700
Data Index: 5306507 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0645. Min Act: -0.1700
Data Index: 122089 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0645. Min Act: -0.1700
Data Index: 2258498 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0645. Min Act: -0.1700
Data Index: 7889795 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0645. Min Act: -0.1700
Data Index: 5263066 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0332. Min Act: -0.1700
Data Index: 1141327 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0332. Min Act: -0.1700
Data Index: 824595 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2207. Min Range: -5.2207
Max Act: 5.0645. Min Act: -0.1700
Data Index: 4348797 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19