Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5556 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.6269. Min Act: -0.1700
Data Index: 7902123 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.6269. Min Act: -0.1700
Data Index: 853847 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.5019. Min Act: -0.1700
Data Index: 7376329 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.4707. Min Act: -0.1700
Data Index: 1550148 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.4707. Min Act: -0.1700
Data Index: 1002986 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.4394. Min Act: -0.1700
Data Index: 6339026 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.3769. Min Act: -0.1700
Data Index: 187744 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.3769. Min Act: -0.1700
Data Index: 1547601 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.3144. Min Act: -0.1700
Data Index: 6670494 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.2832. Min Act: -0.1700
Data Index: 5981635 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.3144. Min Act: -0.1700
Data Index: 8498331 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.1894. Min Act: -0.1700
Data Index: 7058799 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.1894. Min Act: -0.1700
Data Index: 4873271 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.1269. Min Act: -0.1700
Data Index: 8093048 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.1269. Min Act: -0.1700
Data Index: 6218370 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.0957. Min Act: -0.1700
Data Index: 1278793 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.0957. Min Act: -0.1700
Data Index: 7419924 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.0957. Min Act: -0.1700
Data Index: 3877227 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.0019. Min Act: -0.1700
Data Index: 2668941 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6269. Min Range: -7.6269
Max Act: 7.0332. Min Act: -0.1700
Data Index: 8265701 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19