Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 812 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.9653. Min Act: -0.1700
Data Index: 7556052 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.8403. Min Act: -0.1700
Data Index: 4750753 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.9028. Min Act: -0.1700
Data Index: 2443487 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.7778. Min Act: -0.1700
Data Index: 3032920 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.7778. Min Act: -0.1700
Data Index: 7258146 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.7153. Min Act: -0.1700
Data Index: 3587948 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.7778. Min Act: -0.1700
Data Index: 1632626 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.7153. Min Act: -0.1700
Data Index: 2736744 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.6528. Min Act: -0.1700
Data Index: 8531372 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.6528. Min Act: -0.1700
Data Index: 8502460 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.6528. Min Act: -0.1700
Data Index: 6935351 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.5903. Min Act: -0.1700
Data Index: 6209394 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.5903. Min Act: -0.1700
Data Index: 3587950 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.5278. Min Act: -0.1700
Data Index: 4595957 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.5278. Min Act: -0.1700
Data Index: 3176840 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.4028. Min Act: -0.1700
Data Index: 5728512 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.4028. Min Act: -0.1700
Data Index: 6209393 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.4028. Min Act: -0.1700
Data Index: 472885 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.4028. Min Act: -0.1700
Data Index: 196892 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9653. Min Range: -8.9653
Max Act: 8.4028. Min Act: -0.1700
Data Index: 4927244 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19