Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1520 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.3406. Min Act: -0.1700
Data Index: 6670797 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.2781. Min Act: -0.1700
Data Index: 1521504 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.3093. Min Act: -0.1700
Data Index: 5510563 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.2468. Min Act: -0.1700
Data Index: 3017168 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.2156. Min Act: -0.1700
Data Index: 2290426 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.2156. Min Act: -0.1700
Data Index: 8084874 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.2468. Min Act: -0.1700
Data Index: 7291338 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.2156. Min Act: -0.1700
Data Index: 93353 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.1843. Min Act: -0.1700
Data Index: 1579603 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.1531. Min Act: -0.1700
Data Index: 3052274 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.1531. Min Act: -0.1700
Data Index: 3604660 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.1531. Min Act: -0.1700
Data Index: 8661162 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.0906. Min Act: -0.1700
Data Index: 5428381 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.0906. Min Act: -0.1700
Data Index: 6733689 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.1531. Min Act: -0.1700
Data Index: 4760854 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.1218. Min Act: -0.1700
Data Index: 8203820 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.0906. Min Act: -0.1700
Data Index: 2072291 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.0906. Min Act: -0.1700
Data Index: 4987591 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.0906. Min Act: -0.1700
Data Index: 5223076 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3406. Min Range: -6.3406
Max Act: 6.1218. Min Act: -0.1700
Data Index: 7442404 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19