Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 892 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.9877. Min Act: -0.1700
Data Index: 3084841 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.9877. Min Act: -0.1700
Data Index: 1334018 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.9564. Min Act: -0.1700
Data Index: 7420148 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.9564. Min Act: -0.1700
Data Index: 2336 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.9252. Min Act: -0.1700
Data Index: 5559276 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.8939. Min Act: -0.1700
Data Index: 3390104 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.8939. Min Act: -0.1700
Data Index: 6449993 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.8626. Min Act: -0.1700
Data Index: 7975044 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.8313. Min Act: -0.1700
Data Index: 209969 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.8313. Min Act: -0.1700
Data Index: 956080 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.8313. Min Act: -0.1700
Data Index: 117269 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.7688. Min Act: -0.1700
Data Index: 7013147 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.8001. Min Act: -0.1700
Data Index: 524536 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.7688. Min Act: -0.1700
Data Index: 3306030 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.7688. Min Act: -0.1700
Data Index: 8666209 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.7688. Min Act: -0.1700
Data Index: 5321906 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.7375. Min Act: -0.1700
Data Index: 3257487 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.7375. Min Act: -0.1700
Data Index: 5699210 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.7062. Min Act: -0.1700
Data Index: 4548814 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9877. Min Range: -3.9877
Max Act: 3.8001. Min Act: -0.1700
Data Index: 2620832 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19