Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 205 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3343. Min Range: -7.3343
Max Act: 7.3343. Min Act: -0.1700
Data Index: 35771 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3343. Min Range: -7.3343
Max Act: 7.2405. Min Act: -0.1700
Data Index: 2456833 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3343. Min Range: -7.3343
Max Act: 7.2093. Min Act: -0.1700
Data Index: 4814617 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3343. Min Range: -7.3343
Max Act: 7.1468. Min Act: -0.1700
Data Index: 5533501 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3343. Min Range: -7.3343
Max Act: 7.1155. Min Act: -0.1700
Data Index: 368698 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3343. Min Range: -7.3343
Max Act: 7.0530. Min Act: -0.1700
Data Index: 8497057 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.9905. Min Act: -0.1700
Data Index: 1156150 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.9905. Min Act: -0.1700
Data Index: 6987122 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.9593. Min Act: -0.1700
Data Index: 6348356 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.9905. Min Act: -0.1700
Data Index: 5779067 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.9280. Min Act: -0.1700
Data Index: 3719021 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.9280. Min Act: -0.1700
Data Index: 5927783 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.8968. Min Act: -0.1700
Data Index: 2970606 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.8655. Min Act: -0.1700
Data Index: 6276873 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.8655. Min Act: -0.1700
Data Index: 2618669 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.8343. Min Act: -0.1700
Data Index: 1185361 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.8655. Min Act: -0.1700
Data Index: 8767724 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.8655. Min Act: -0.1700
Data Index: 3787333 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.8343. Min Act: -0.1700
Data Index: 916966 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3343. Min Range: -7.3343
Max Act: 6.8030. Min Act: -0.1700
Data Index: 2624075 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19