Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3619 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7840. Min Range: -8.7840
Max Act: 8.7840. Min Act: -0.1700
Data Index: 2791772 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7840. Min Range: -8.7840
Max Act: 8.3465. Min Act: -0.1700
Data Index: 7396484 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7840. Min Range: -8.7840
Max Act: 8.1590. Min Act: -0.1700
Data Index: 5219250 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.7840. Min Act: -0.1700
Data Index: 5129309 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.7215. Min Act: -0.1700
Data Index: 6374572 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.6590. Min Act: -0.1700
Data Index: 5397626 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.5965. Min Act: -0.1700
Data Index: 3827586 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.5965. Min Act: -0.1700
Data Index: 4059721 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.5653. Min Act: -0.1700
Data Index: 8597449 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.5653. Min Act: -0.1700
Data Index: 7342051 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.5965. Min Act: -0.1700
Data Index: 8488774 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.5653. Min Act: -0.1700
Data Index: 2825012 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.5340. Min Act: -0.1700
Data Index: 5753959 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.5340. Min Act: -0.1700
Data Index: 220119 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.5028. Min Act: -0.1700
Data Index: 4325585 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.5028. Min Act: -0.1700
Data Index: 8702068 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.5028. Min Act: -0.1700
Data Index: 260039 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.4715. Min Act: -0.1700
Data Index: 3773848 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.4715. Min Act: -0.1700
Data Index: 4297631 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7840. Min Range: -8.7840
Max Act: 7.4090. Min Act: -0.1700
Data Index: 5372925 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19