Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 485 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.5877. Min Act: -0.1700
Data Index: 604543 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.5565. Min Act: -0.1700
Data Index: 616136 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.4315. Min Act: -0.1700
Data Index: 7020178 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.4315. Min Act: -0.1700
Data Index: 173878 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.4315. Min Act: -0.1700
Data Index: 1957228 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.3065. Min Act: -0.1700
Data Index: 2880841 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.3065. Min Act: -0.1700
Data Index: 209950 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.3065. Min Act: -0.1700
Data Index: 5019020 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.3065. Min Act: -0.1700
Data Index: 8764950 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.2752. Min Act: -0.1700
Data Index: 1743261 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.2440. Min Act: -0.1700
Data Index: 8365258 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.2127. Min Act: -0.1700
Data Index: 142848 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.2127. Min Act: -0.1700
Data Index: 2107660 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.2127. Min Act: -0.1700
Data Index: 3366854 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.2127. Min Act: -0.1700
Data Index: 5664115 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.1815. Min Act: -0.1700
Data Index: 7453660 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.1815. Min Act: -0.1700
Data Index: 3365799 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.1502. Min Act: -0.1700
Data Index: 1838109 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.0877. Min Act: -0.1700
Data Index: 6336869 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5877. Min Range: -6.5877
Max Act: 6.0877. Min Act: -0.1700
Data Index: 6896498 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19