Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.9046. Min Act: -0.1700
Data Index: 466669 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.6859. Min Act: -0.1700
Data Index: 637733 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.6234. Min Act: -0.1700
Data Index: 987482 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.6234. Min Act: -0.1700
Data Index: 6438932 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.6234. Min Act: -0.1700
Data Index: 1108697 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.5921. Min Act: -0.1700
Data Index: 5675332 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.5921. Min Act: -0.1700
Data Index: 4100705 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.5609. Min Act: -0.1700
Data Index: 988828 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.5921. Min Act: -0.1700
Data Index: 6747177 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.5921. Min Act: -0.1700
Data Index: 1155202 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.5609. Min Act: -0.1700
Data Index: 6788629 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.5609. Min Act: -0.1700
Data Index: 8118494 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.5609. Min Act: -0.1700
Data Index: 6656031 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.5609. Min Act: -0.1700
Data Index: 8444054 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.4984. Min Act: -0.1700
Data Index: 1173718 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.5296. Min Act: -0.1700
Data Index: 1625426 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.5296. Min Act: -0.1700
Data Index: 1570761 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.4984. Min Act: -0.1700
Data Index: 4210868 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.4984. Min Act: -0.1700
Data Index: 5413505 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9046. Min Range: -5.9046
Max Act: 5.4984. Min Act: -0.1700
Data Index: 647037 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19