Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1102 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0636. Min Range: -5.0636
Max Act: 5.0636. Min Act: -0.1700
Data Index: 210588 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0636. Min Range: -5.0636
Max Act: 5.0636. Min Act: -0.1700
Data Index: 8532676 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0636. Min Range: -5.0636
Max Act: 5.0636. Min Act: -0.1700
Data Index: 1495358 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0636. Min Range: -5.0636
Max Act: 5.0323. Min Act: -0.1700
Data Index: 297437 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0636. Min Range: -5.0636
Max Act: 5.0011. Min Act: -0.1700
Data Index: 6122398 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9698. Min Act: -0.1700
Data Index: 8005999 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9698. Min Act: -0.1700
Data Index: 8453242 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9698. Min Act: -0.1700
Data Index: 2999939 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9386. Min Act: -0.1700
Data Index: 4350715 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9386. Min Act: -0.1700
Data Index: 4731985 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9073. Min Act: -0.1700
Data Index: 1279296 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9386. Min Act: -0.1700
Data Index: 7906500 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9386. Min Act: -0.1700
Data Index: 3040260 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9073. Min Act: -0.1700
Data Index: 1279294 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9386. Min Act: -0.1700
Data Index: 8086220 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9073. Min Act: -0.1700
Data Index: 3737874 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9073. Min Act: -0.1700
Data Index: 1111442 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9386. Min Act: -0.1700
Data Index: 5048142 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.9073. Min Act: -0.1700
Data Index: 5078405 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0636. Min Range: -5.0636
Max Act: 4.8761. Min Act: -0.1700
Data Index: 6886974 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19