Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3022 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0167. Min Range: -8.0167
Max Act: 8.0167. Min Act: -0.1700
Data Index: 8234739 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.8605. Min Act: -0.1700
Data Index: 1868062 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.8292. Min Act: -0.1700
Data Index: 5706452 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.8292. Min Act: -0.1700
Data Index: 6276678 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.8292. Min Act: -0.1700
Data Index: 3298124 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.7667. Min Act: -0.1700
Data Index: 2119427 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.7667. Min Act: -0.1700
Data Index: 2877636 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.7667. Min Act: -0.1700
Data Index: 7957896 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.7355. Min Act: -0.1700
Data Index: 2763613 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.7667. Min Act: -0.1700
Data Index: 8701537 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.7355. Min Act: -0.1700
Data Index: 2389560 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.7042. Min Act: -0.1700
Data Index: 1397124 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.7042. Min Act: -0.1700
Data Index: 646391 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.6730. Min Act: -0.1700
Data Index: 5853161 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.6105. Min Act: -0.1700
Data Index: 5145283 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.6105. Min Act: -0.1700
Data Index: 448479 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.5792. Min Act: -0.1700
Data Index: 5059909 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.5792. Min Act: -0.1700
Data Index: 4154081 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.5480. Min Act: -0.1700
Data Index: 202667 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0167. Min Range: -8.0167
Max Act: 7.5792. Min Act: -0.1700
Data Index: 2011322 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19