Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5088 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.7146. Min Act: -0.1700
Data Index: 8387153 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.6521. Min Act: -0.1700
Data Index: 2266188 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.4959. Min Act: -0.1700
Data Index: 1145124 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.4959. Min Act: -0.1700
Data Index: 1815974 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.4959. Min Act: -0.1700
Data Index: 3584428 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.3709. Min Act: -0.1700
Data Index: 1856070 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.3709. Min Act: -0.1700
Data Index: 7301330 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.3396. Min Act: -0.1700
Data Index: 4249608 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.3396. Min Act: -0.1700
Data Index: 3611948 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.3084. Min Act: -0.1700
Data Index: 8734240 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.3084. Min Act: -0.1700
Data Index: 6603918 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.3084. Min Act: -0.1700
Data Index: 8183598 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.2771. Min Act: -0.1700
Data Index: 8780590 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.2459. Min Act: -0.1700
Data Index: 5448296 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.2146. Min Act: -0.1700
Data Index: 2655861 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.2146. Min Act: -0.1700
Data Index: 4135116 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.1521. Min Act: -0.1700
Data Index: 1955145 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.1834. Min Act: -0.1700
Data Index: 2753866 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.1834. Min Act: -0.1700
Data Index: 7185955 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7146. Min Range: -6.7146
Max Act: 6.1834. Min Act: -0.1700
Data Index: 2646642 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19