Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.5989. Min Act: -0.1700
Data Index: 6287545 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.5362. Min Act: -0.1700
Data Index: 3889555 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.5206. Min Act: -0.1700
Data Index: 5227452 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.5049. Min Act: -0.1700
Data Index: 1112617 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.4109. Min Act: -0.1700
Data Index: 4315381 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.3796. Min Act: -0.1700
Data Index: 6811834 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.3325. Min Act: -0.1700
Data Index: 8054822 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.3325. Min Act: -0.1700
Data Index: 3258784 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.3325. Min Act: -0.1700
Data Index: 8739988 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.3011. Min Act: -0.1700
Data Index: 1141234 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.3168. Min Act: -0.1700
Data Index: 2163454 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.3011. Min Act: -0.1700
Data Index: 5266647 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.2854. Min Act: -0.1700
Data Index: 824966 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.2854. Min Act: -0.1700
Data Index: 8037113 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.2697. Min Act: -0.1700
Data Index: 7606948 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.2540. Min Act: -0.1700
Data Index: 7074184 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.2383. Min Act: -0.1700
Data Index: 2573333 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.2383. Min Act: -0.1700
Data Index: 4946774 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.2383. Min Act: -0.1700
Data Index: 8816585 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5989. Min Range: -3.5989
Max Act: 3.2383. Min Act: -0.1700
Data Index: 3087293 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19