Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.8482. Min Act: -0.1700
Data Index: 6788064 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.7545. Min Act: -0.1700
Data Index: 8716963 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.6920. Min Act: -0.1700
Data Index: 6442984 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.6920. Min Act: -0.1700
Data Index: 8774753 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.6295. Min Act: -0.1700
Data Index: 7606472 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.5670. Min Act: -0.1699
Data Index: 7674969 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.5982. Min Act: -0.1700
Data Index: 1162336 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.5045. Min Act: -0.1700
Data Index: 248141 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.5045. Min Act: -0.1687
Data Index: 1577237 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.4420. Min Act: -0.1700
Data Index: 2810820 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.4420. Min Act: -0.1700
Data Index: 1723271 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.4420. Min Act: -0.1698
Data Index: 3260466 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.4107. Min Act: -0.1700
Data Index: 4367312 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.4107. Min Act: -0.1700
Data Index: 868530 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.4107. Min Act: -0.1700
Data Index: 1987116 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.4107. Min Act: -0.1700
Data Index: 2472895 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.3795. Min Act: -0.1700
Data Index: 4295915 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.3795. Min Act: -0.1700
Data Index: 5837139 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.3795. Min Act: -0.1700
Data Index: 1561699 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8482. Min Range: -5.8482
Max Act: 5.3795. Min Act: -0.1700
Data Index: 7656040 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19