Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2968. Min Range: -8.2968
Max Act: 8.2968. Min Act: -0.1700
Data Index: 3785401 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2968. Min Range: -8.2968
Max Act: 8.0468. Min Act: -0.1700
Data Index: 3184789 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2968. Min Range: -8.2968
Max Act: 8.0468. Min Act: -0.1700
Data Index: 7341051 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.9843. Min Act: -0.1700
Data Index: 3478758 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.9218. Min Act: -0.1700
Data Index: 3037524 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.9218. Min Act: -0.1700
Data Index: 1894169 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.9218. Min Act: -0.1700
Data Index: 7563397 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.7968. Min Act: -0.1700
Data Index: 2132928 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.6093. Min Act: -0.1700
Data Index: 8366068 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.6093. Min Act: -0.1700
Data Index: 1416538 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.6093. Min Act: -0.1700
Data Index: 4345058 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.6093. Min Act: -0.1700
Data Index: 6719474 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.6093. Min Act: -0.1700
Data Index: 8065349 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.5468. Min Act: -0.1700
Data Index: 42508 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.5156. Min Act: -0.1700
Data Index: 7832915 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.5156. Min Act: -0.1700
Data Index: 3159129 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.4843. Min Act: -0.1700
Data Index: 1693878 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.4843. Min Act: -0.1700
Data Index: 4174872 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.4843. Min Act: -0.1699
Data Index: 1654109 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2968. Min Range: -8.2968
Max Act: 7.4218. Min Act: -0.1700
Data Index: 710433 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19