Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0855. Min Range: -5.0855
Max Act: 5.0855. Min Act: -0.1700
Data Index: 8424877 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.9918. Min Act: -0.1700
Data Index: 5237218 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.9605. Min Act: -0.1700
Data Index: 3784178 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.9605. Min Act: -0.1700
Data Index: 6920022 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.9605. Min Act: -0.1700
Data Index: 6014434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.8668. Min Act: -0.1700
Data Index: 3897380 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.8355. Min Act: -0.1700
Data Index: 5829905 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.7730. Min Act: -0.1700
Data Index: 7733127 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.7418. Min Act: -0.1700
Data Index: 1508471 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.7418. Min Act: -0.1700
Data Index: 4212974 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.7105. Min Act: -0.1700
Data Index: 1907536 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.7418. Min Act: -0.1700
Data Index: 5829898 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.7105. Min Act: -0.1700
Data Index: 8191588 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.7105. Min Act: -0.1700
Data Index: 4127769 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.6793. Min Act: -0.1700
Data Index: 5442941 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.6793. Min Act: -0.1700
Data Index: 4291122 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.6793. Min Act: -0.1700
Data Index: 5829906 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.7105. Min Act: -0.1700
Data Index: 1700511 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.6168. Min Act: -0.1700
Data Index: 3514226 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0855. Min Range: -5.0855
Max Act: 4.6480. Min Act: -0.1700
Data Index: 5829901 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19