Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 509 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1618. Min Range: -6.1618
Max Act: 6.1618. Min Act: -0.1700
Data Index: 2210054 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1618. Min Range: -6.1618
Max Act: 6.0993. Min Act: -0.1700
Data Index: 213743 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1618. Min Range: -6.1618
Max Act: 6.0368. Min Act: -0.1700
Data Index: 5223085 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1618. Min Range: -6.1618
Max Act: 6.0056. Min Act: -0.1700
Data Index: 4771826 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1618. Min Range: -6.1618
Max Act: 6.0056. Min Act: -0.1700
Data Index: 1304767 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.9431. Min Act: -0.1700
Data Index: 6620971 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.8806. Min Act: -0.1700
Data Index: 2065678 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.9118. Min Act: -0.1700
Data Index: 2098783 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.8806. Min Act: -0.1700
Data Index: 2141883 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.8493. Min Act: -0.1700
Data Index: 8062400 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.8806. Min Act: -0.1700
Data Index: 7022940 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.8493. Min Act: -0.1700
Data Index: 506152 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.8181. Min Act: -0.1700
Data Index: 7483436 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.8181. Min Act: -0.1700
Data Index: 6263228 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.7868. Min Act: -0.1700
Data Index: 452436 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.8181. Min Act: -0.1700
Data Index: 3262752 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.7556. Min Act: -0.1700
Data Index: 3019027 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.7556. Min Act: -0.1700
Data Index: 5054626 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.7556. Min Act: -0.1700
Data Index: 1943517 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1618. Min Range: -6.1618
Max Act: 5.7556. Min Act: -0.1700
Data Index: 7391506 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19