Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1704 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.8604. Min Act: -0.1700
Data Index: 1204309 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.4541. Min Act: -0.1700
Data Index: 7448033 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.3916. Min Act: -0.1700
Data Index: 1121344 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.4541. Min Act: -0.1700
Data Index: 451934 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.3916. Min Act: -0.1700
Data Index: 6315518 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.3291. Min Act: -0.1700
Data Index: 1623041 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.3291. Min Act: -0.1700
Data Index: 3846328 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.2666. Min Act: -0.1700
Data Index: 7289235 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.2354. Min Act: -0.1700
Data Index: 3849186 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.2041. Min Act: -0.1700
Data Index: 8150080 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.1729. Min Act: -0.1700
Data Index: 1008953 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.1729. Min Act: -0.1700
Data Index: 4385474 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.1416. Min Act: -0.1700
Data Index: 1475601 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.1416. Min Act: -0.1700
Data Index: 5989963 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.1104. Min Act: -0.1700
Data Index: 5175926 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.1104. Min Act: -0.1700
Data Index: 2063410 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.0791. Min Act: -0.1700
Data Index: 1756517 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.0791. Min Act: -0.1700
Data Index: 5993819 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.0479. Min Act: -0.1700
Data Index: 5786000 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8604. Min Range: -6.8604
Max Act: 6.0479. Min Act: -0.1700
Data Index: 5790362 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #19