Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.8324. Min Act: -0.1700
Data Index: 574479 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.8324. Min Act: -0.1700
Data Index: 7190693 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.7074. Min Act: -0.1700
Data Index: 8003852 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.7074. Min Act: -0.1700
Data Index: 5098914 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.6762. Min Act: -0.1700
Data Index: 6078762 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.6762. Min Act: -0.1700
Data Index: 4112601 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.7074. Min Act: -0.1700
Data Index: 3778804 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.6449. Min Act: -0.1700
Data Index: 5740630 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.6137. Min Act: -0.1700
Data Index: 3110184 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.6137. Min Act: -0.1700
Data Index: 4669411 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.6137. Min Act: -0.1700
Data Index: 7488089 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.5824. Min Act: -0.1700
Data Index: 1020163 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.6137. Min Act: -0.1700
Data Index: 7062301 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.5824. Min Act: -0.1700
Data Index: 3118973 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.5199. Min Act: -0.1700
Data Index: 785457 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.5512. Min Act: -0.1700
Data Index: 2155843 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.5512. Min Act: -0.1700
Data Index: 3706160 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.5199. Min Act: -0.1700
Data Index: 2853832 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.5199. Min Act: -0.1700
Data Index: 7870016 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8324. Min Range: -4.8324
Max Act: 4.5199. Min Act: -0.1700
Data Index: 6078771 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19