Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 604 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.1250. Min Act: -0.1700
Data Index: 5916462 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0938. Min Act: -0.1700
Data Index: 810736 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0938. Min Act: -0.1700
Data Index: 4257962 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0625. Min Act: -0.1700
Data Index: 1195068 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0625. Min Act: -0.1700
Data Index: 5353836 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0625. Min Act: -0.1700
Data Index: 5461340 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0625. Min Act: -0.1700
Data Index: 7007848 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0625. Min Act: -0.1700
Data Index: 6843603 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0625. Min Act: -0.1700
Data Index: 6860752 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0312. Min Act: -0.1700
Data Index: 6557145 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0312. Min Act: -0.1700
Data Index: 3041732 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0312. Min Act: -0.1700
Data Index: 8598710 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0000. Min Act: -0.1700
Data Index: 7958915 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0312. Min Act: -0.1700
Data Index: 5753541 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0312. Min Act: -0.1700
Data Index: 1675168 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0312. Min Act: -0.1700
Data Index: 363275 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0625. Min Act: -0.1700
Data Index: 1649331 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0312. Min Act: -0.1700
Data Index: 4287386 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1250. Min Range: -4.1250
Max Act: 3.9687. Min Act: -0.1700
Data Index: 3012250 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1250. Min Range: -4.1250
Max Act: 4.0312. Min Act: -0.1700
Data Index: 3526130 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19