Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2340. Min Range: -6.2340
Max Act: 6.2340. Min Act: -0.1700
Data Index: 6586620 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2340. Min Range: -6.2340
Max Act: 6.1090. Min Act: -0.1700
Data Index: 2842700 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2340. Min Range: -6.2340
Max Act: 6.1403. Min Act: -0.1700
Data Index: 8546619 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2340. Min Range: -6.2340
Max Act: 6.0778. Min Act: -0.1700
Data Index: 1010258 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.9528. Min Act: -0.1700
Data Index: 8786829 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.9840. Min Act: -0.1700
Data Index: 1811454 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.9840. Min Act: -0.1700
Data Index: 975488 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.9528. Min Act: -0.1700
Data Index: 2396508 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.9528. Min Act: -0.1700
Data Index: 4094608 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.9528. Min Act: -0.1700
Data Index: 4428621 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.8903. Min Act: -0.1700
Data Index: 3600754 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.8903. Min Act: -0.1700
Data Index: 5265317 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.8903. Min Act: -0.1700
Data Index: 2853710 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.8590. Min Act: -0.1700
Data Index: 7611439 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.7965. Min Act: -0.1700
Data Index: 1820422 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.8278. Min Act: -0.1700
Data Index: 8770561 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.8278. Min Act: -0.1700
Data Index: 6928211 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.7965. Min Act: -0.1700
Data Index: 558612 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.8278. Min Act: -0.1700
Data Index: 745350 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2340. Min Range: -6.2340
Max Act: 5.7965. Min Act: -0.1700
Data Index: 7840637 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19