Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3655 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.5009. Min Act: -0.1696
Data Index: 613396 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.4697. Min Act: -0.1699
Data Index: 5408031 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.4384. Min Act: -0.1700
Data Index: 2708730 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.4384. Min Act: -0.1700
Data Index: 7645912 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.4384. Min Act: -0.1700
Data Index: 692383 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3759. Min Act: -0.1700
Data Index: 389560 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3759. Min Act: -0.1700
Data Index: 5942894 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3759. Min Act: -0.1700
Data Index: 1454749 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3759. Min Act: -0.1698
Data Index: 401489 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3447. Min Act: -0.1700
Data Index: 7934813 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3134. Min Act: -0.1700
Data Index: 2635594 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3447. Min Act: -0.1700
Data Index: 587757 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3447. Min Act: -0.1700
Data Index: 686734 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3447. Min Act: -0.1700
Data Index: 2747604 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3447. Min Act: -0.1700
Data Index: 3393710 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.2822. Min Act: -0.1700
Data Index: 2428122 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3134. Min Act: -0.1700
Data Index: 5977831 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3134. Min Act: -0.1700
Data Index: 7565453 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3134. Min Act: -0.1700
Data Index: 1525250 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5009. Min Range: -6.5009
Max Act: 6.3134. Min Act: -0.1700
Data Index: 1808233 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19