Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1090. Min Range: -7.1090
Max Act: 7.1090. Min Act: -0.1700
Data Index: 1110958 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.9215. Min Act: -0.1700
Data Index: 5113368 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.7965. Min Act: -0.1700
Data Index: 8714963 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.7652. Min Act: -0.1700
Data Index: 6574033 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.7027. Min Act: -0.1700
Data Index: 7957693 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.6715. Min Act: -0.1699
Data Index: 7957692 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.6715. Min Act: -0.1700
Data Index: 431905 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.6402. Min Act: -0.1700
Data Index: 7213508 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.6090. Min Act: -0.1700
Data Index: 7448973 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.6402. Min Act: -0.1700
Data Index: 6926080 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.6090. Min Act: -0.1700
Data Index: 1327171 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.5777. Min Act: -0.1700
Data Index: 3203535 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.5465. Min Act: -0.1700
Data Index: 2963524 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.5465. Min Act: -0.1700
Data Index: 4132847 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.5465. Min Act: -0.1700
Data Index: 7237368 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.4840. Min Act: -0.1700
Data Index: 7788203 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.5152. Min Act: -0.1700
Data Index: 2429003 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.4840. Min Act: -0.1700
Data Index: 6533441 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.4840. Min Act: -0.1700
Data Index: 2963522 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1090. Min Range: -7.1090
Max Act: 6.4527. Min Act: -0.1700
Data Index: 6838913 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19