Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0832. Min Range: -6.0832
Max Act: 6.0832. Min Act: -0.1700
Data Index: 7121703 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.9894. Min Act: -0.1700
Data Index: 2042584 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.9582. Min Act: -0.1700
Data Index: 482241 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.9269. Min Act: -0.1700
Data Index: 5801279 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.9269. Min Act: -0.1700
Data Index: 4635632 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.8957. Min Act: -0.1700
Data Index: 3669 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.8957. Min Act: -0.1700
Data Index: 3303651 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.8957. Min Act: -0.1700
Data Index: 6501086 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.9269. Min Act: -0.1700
Data Index: 7570618 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.8019. Min Act: -0.1700
Data Index: 5927263 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.8332. Min Act: -0.1699
Data Index: 1144430 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.8644. Min Act: -0.1700
Data Index: 3129673 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.8332. Min Act: -0.1700
Data Index: 8730084 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.8019. Min Act: -0.1700
Data Index: 352500 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.8019. Min Act: -0.1700
Data Index: 4763167 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.8019. Min Act: -0.1700
Data Index: 6120567 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.8019. Min Act: -0.1700
Data Index: 143790 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.7707. Min Act: -0.1700
Data Index: 2168727 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.7707. Min Act: -0.1700
Data Index: 6102298 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0832. Min Range: -6.0832
Max Act: 5.7707. Min Act: -0.1700
Data Index: 2232781 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19