Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.4096. Min Act: -0.1700
Data Index: 650563 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.3933. Min Act: -0.1700
Data Index: 1945522 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.2123. Min Act: -0.1700
Data Index: 2743673 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1958. Min Act: -0.1700
Data Index: 1956060 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1791. Min Act: -0.1700
Data Index: 456773 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1958. Min Act: -0.1700
Data Index: 4721619 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1791. Min Act: -0.1700
Data Index: 278277 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1958. Min Act: -0.1700
Data Index: 17906 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1958. Min Act: -0.1700
Data Index: 1085203 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1458. Min Act: -0.1700
Data Index: 7314601 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1625. Min Act: -0.1700
Data Index: 4731192 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1458. Min Act: -0.1700
Data Index: 3793175 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1458. Min Act: -0.1700
Data Index: 311577 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1458. Min Act: -0.1700
Data Index: 7974774 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1458. Min Act: -0.1700
Data Index: 31907 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1292. Min Act: -0.1700
Data Index: 6975061 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1292. Min Act: -0.1700
Data Index: 4946934 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1292. Min Act: -0.1700
Data Index: 2113089 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1124. Min Act: -0.1700
Data Index: 2342977 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4096. Min Range: -2.4096
Max Act: 2.1292. Min Act: -0.1699
Data Index: 1697636 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19