Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1164 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.9898. Min Act: -0.1700
Data Index: 444210 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.9585. Min Act: -0.1700
Data Index: 8453661 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.9585. Min Act: -0.1700
Data Index: 8643355 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8648. Min Act: -0.1700
Data Index: 7922821 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8335. Min Act: -0.1700
Data Index: 2391070 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.8023. Min Act: -0.1700
Data Index: 8760930 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.7085. Min Act: -0.1700
Data Index: 3364355 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.6773. Min Act: -0.1700
Data Index: 8695059 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.6773. Min Act: -0.1700
Data Index: 2800117 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.6460. Min Act: -0.1700
Data Index: 2900244 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.6460. Min Act: -0.1700
Data Index: 4225317 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.6148. Min Act: -0.1700
Data Index: 1709671 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.6148. Min Act: -0.1700
Data Index: 3744879 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.6148. Min Act: -0.1700
Data Index: 6167861 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.6148. Min Act: -0.1700
Data Index: 7320230 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.5835. Min Act: -0.1700
Data Index: 5226952 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.5835. Min Act: -0.1700
Data Index: 3212615 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.5523. Min Act: -0.1700
Data Index: 8487150 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.4273. Min Act: -0.1700
Data Index: 3983861 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9898. Min Range: -5.9898
Max Act: 5.4273. Min Act: -0.1700
Data Index: 3867149 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19