Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 772 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.7641. Min Act: -0.1700
Data Index: 7576364 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.5764. Min Act: -0.1700
Data Index: 1693679 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.3414. Min Act: -0.1700
Data Index: 5078871 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.2472. Min Act: -0.1700
Data Index: 4805818 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.2157. Min Act: -0.1700
Data Index: 4860086 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.2314. Min Act: -0.1700
Data Index: 3900916 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.1843. Min Act: -0.1700
Data Index: 5775204 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.1685. Min Act: -0.1700
Data Index: 6065407 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.1528. Min Act: -0.1697
Data Index: 3058498 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.1528. Min Act: -0.1700
Data Index: 6977348 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.0898. Min Act: -0.1700
Data Index: 8086594 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.0898. Min Act: -0.1700
Data Index: 7042056 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.0898. Min Act: -0.1700
Data Index: 7754663 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.0740. Min Act: -0.1700
Data Index: 6154094 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.0582. Min Act: -0.1700
Data Index: 6054212 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.0582. Min Act: -0.1700
Data Index: 3749014 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.0425. Min Act: -0.1700
Data Index: 5398803 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.0109. Min Act: -0.1700
Data Index: 6439473 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.0267. Min Act: -0.1700
Data Index: 3183763 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7641. Min Range: -3.7641
Max Act: 3.0109. Min Act: -0.1700
Data Index: 1644796 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19