Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6391 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.6422. Min Act: -0.1700
Data Index: 5210187 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.4547. Min Act: -0.1700
Data Index: 1070052 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.4547. Min Act: -0.1700
Data Index: 7505635 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.4235. Min Act: -0.1700
Data Index: 6345216 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.3297. Min Act: -0.1700
Data Index: 2074834 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.2985. Min Act: -0.1700
Data Index: 7348842 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.2985. Min Act: -0.1700
Data Index: 2680689 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.2360. Min Act: -0.1700
Data Index: 5148306 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.2047. Min Act: -0.1700
Data Index: 4626123 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.2360. Min Act: -0.1700
Data Index: 2646797 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.1735. Min Act: -0.1700
Data Index: 1113809 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.1735. Min Act: -0.1700
Data Index: 3325361 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.1422. Min Act: -0.1700
Data Index: 1557581 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.1735. Min Act: -0.1700
Data Index: 8208421 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.1422. Min Act: -0.1700
Data Index: 1759238 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.1422. Min Act: -0.1700
Data Index: 6916017 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.1422. Min Act: -0.1700
Data Index: 3601522 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.1422. Min Act: -0.1700
Data Index: 7877871 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.1422. Min Act: -0.1700
Data Index: 4727367 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6422. Min Range: -4.6422
Max Act: 4.1422. Min Act: -0.1700
Data Index: 2357945 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19