Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5040 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.4755. Min Act: -0.1700
Data Index: 2886016 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.2255. Min Act: -0.1700
Data Index: 532864 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.2255. Min Act: -0.1700
Data Index: 183568 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.2255. Min Act: -0.1700
Data Index: 2045392 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.1630. Min Act: -0.1700
Data Index: 3819959 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.1005. Min Act: -0.1700
Data Index: 1979297 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.1005. Min Act: -0.1700
Data Index: 7497674 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.1005. Min Act: -0.1700
Data Index: 7352144 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.1005. Min Act: -0.1700
Data Index: 8316149 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.1005. Min Act: -0.1700
Data Index: 2348136 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.0380. Min Act: -0.1700
Data Index: 5904636 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4755. Min Range: -8.4755
Max Act: 8.0380. Min Act: -0.1700
Data Index: 265206 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4755. Min Range: -8.4755
Max Act: 7.9755. Min Act: -0.1700
Data Index: 7572133 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4755. Min Range: -8.4755
Max Act: 7.9755. Min Act: -0.1700
Data Index: 6076412 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4755. Min Range: -8.4755
Max Act: 7.8505. Min Act: -0.1700
Data Index: 6291867 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4755. Min Range: -8.4755
Max Act: 7.8505. Min Act: -0.1700
Data Index: 7707872 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4755. Min Range: -8.4755
Max Act: 7.7880. Min Act: -0.1700
Data Index: 6814025 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4755. Min Range: -8.4755
Max Act: 7.7880. Min Act: -0.1700
Data Index: 2969907 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4755. Min Range: -8.4755
Max Act: 7.7880. Min Act: -0.1700
Data Index: 5611226 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4755. Min Range: -8.4755
Max Act: 7.7880. Min Act: -0.1700
Data Index: 4971904 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19