Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 851 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.5927. Min Act: -0.1700
Data Index: 5259356 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.5927. Min Act: -0.1700
Data Index: 4204163 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.5614. Min Act: -0.1700
Data Index: 6109779 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.5614. Min Act: -0.1700
Data Index: 7190504 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.5614. Min Act: -0.1700
Data Index: 4639521 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.5614. Min Act: -0.1700
Data Index: 2452114 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4677. Min Act: -0.1700
Data Index: 6821066 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4989. Min Act: -0.1700
Data Index: 1799125 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4989. Min Act: -0.1700
Data Index: 4204165 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4989. Min Act: -0.1700
Data Index: 6406667 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4677. Min Act: -0.1700
Data Index: 4967446 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4364. Min Act: -0.1700
Data Index: 1728277 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4677. Min Act: -0.1699
Data Index: 1940030 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4677. Min Act: -0.1700
Data Index: 1940031 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4052. Min Act: -0.1699
Data Index: 2542390 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4052. Min Act: -0.1700
Data Index: 1631193 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4364. Min Act: -0.1700
Data Index: 799436 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4364. Min Act: -0.1700
Data Index: 4337728 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4364. Min Act: -0.1700
Data Index: 5612200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5927. Min Range: -6.5927
Max Act: 6.4364. Min Act: -0.1700
Data Index: 497891 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19