Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.6183. Min Act: -0.1700
Data Index: 4595460 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.3995. Min Act: -0.1700
Data Index: 3720562 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.3058. Min Act: -0.1700
Data Index: 2895877 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.3058. Min Act: -0.1700
Data Index: 4563700 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.3058. Min Act: -0.1700
Data Index: 7226927 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.2745. Min Act: -0.1700
Data Index: 8262317 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.2745. Min Act: -0.1700
Data Index: 7026494 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.2433. Min Act: -0.1700
Data Index: 1461840 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.1808. Min Act: -0.1700
Data Index: 8796383 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.1808. Min Act: -0.1700
Data Index: 17359 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.1495. Min Act: -0.1700
Data Index: 5074867 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.1495. Min Act: -0.1700
Data Index: 1362632 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.1495. Min Act: -0.1700
Data Index: 1992357 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.1495. Min Act: -0.1700
Data Index: 7595339 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.1183. Min Act: -0.1700
Data Index: 2938822 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.1183. Min Act: -0.1700
Data Index: 5568530 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.1183. Min Act: -0.1700
Data Index: 3218910 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.1183. Min Act: -0.1700
Data Index: 1008112 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.0870. Min Act: -0.1700
Data Index: 3830422 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6183. Min Range: -4.6183
Max Act: 4.0870. Min Act: -0.1700
Data Index: 2324981 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19