Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3843 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2546. Min Range: -5.2546
Max Act: 5.2546. Min Act: -0.1700
Data Index: 7777875 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2546. Min Range: -5.2546
Max Act: 5.1609. Min Act: -0.1700
Data Index: 16385 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2546. Min Range: -5.2546
Max Act: 5.1609. Min Act: -0.1700
Data Index: 1845175 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2546. Min Range: -5.2546
Max Act: 5.0671. Min Act: -0.1700
Data Index: 4191310 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2546. Min Range: -5.2546
Max Act: 5.0671. Min Act: -0.1700
Data Index: 1151994 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2546. Min Range: -5.2546
Max Act: 5.0046. Min Act: -0.1700
Data Index: 4124595 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2546. Min Range: -5.2546
Max Act: 5.0359. Min Act: -0.1700
Data Index: 4937809 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2546. Min Range: -5.2546
Max Act: 5.0046. Min Act: -0.1700
Data Index: 8386729 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2546. Min Range: -5.2546
Max Act: 5.0046. Min Act: -0.1700
Data Index: 1521673 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2546. Min Range: -5.2546
Max Act: 4.9421. Min Act: -0.1700
Data Index: 5264566 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2546. Min Range: -5.2546
Max Act: 4.9734. Min Act: -0.1700
Data Index: 3777274 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2546. Min Range: -5.2546
Max Act: 4.9734. Min Act: -0.1700
Data Index: 3837012 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2546. Min Range: -5.2546
Max Act: 4.9734. Min Act: -0.1700
Data Index: 4960028 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2546. Min Range: -5.2546
Max Act: 4.9734. Min Act: -0.1700
Data Index: 8434140 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2546. Min Range: -5.2546
Max Act: 4.9734. Min Act: -0.1700
Data Index: 8272982 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2546. Min Range: -5.2546
Max Act: 4.9734. Min Act: -0.1700
Data Index: 7126773 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2546. Min Range: -5.2546
Max Act: 4.9109. Min Act: -0.1700
Data Index: 2438884 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2546. Min Range: -5.2546
Max Act: 4.9421. Min Act: -0.1700
Data Index: 838302 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2546. Min Range: -5.2546
Max Act: 4.9734. Min Act: -0.1700
Data Index: 3567945 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2546. Min Range: -5.2546
Max Act: 4.9109. Min Act: -0.1700
Data Index: 4191309 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19