Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 744 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4522. Min Range: -6.4522
Max Act: 6.4522. Min Act: -0.1700
Data Index: 23512 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4522. Min Range: -6.4522
Max Act: 6.1397. Min Act: -0.1700
Data Index: 2668509 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4522. Min Range: -6.4522
Max Act: 6.0147. Min Act: -0.1700
Data Index: 3814123 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.9522. Min Act: -0.1700
Data Index: 1519955 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.9835. Min Act: -0.1700
Data Index: 883999 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.9210. Min Act: -0.1700
Data Index: 1319931 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.9210. Min Act: -0.1700
Data Index: 5469644 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.8897. Min Act: -0.1700
Data Index: 1576275 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.8585. Min Act: -0.1700
Data Index: 4833912 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.8897. Min Act: -0.1700
Data Index: 873916 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.8585. Min Act: -0.1700
Data Index: 6061360 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.8585. Min Act: -0.1700
Data Index: 7773269 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.8272. Min Act: -0.1700
Data Index: 4515553 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.7647. Min Act: -0.1700
Data Index: 4827648 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.7960. Min Act: -0.1700
Data Index: 2331863 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.7335. Min Act: -0.1700
Data Index: 7703792 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.7335. Min Act: -0.1700
Data Index: 7441672 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.6710. Min Act: -0.1700
Data Index: 3717192 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.6085. Min Act: -0.1700
Data Index: 6149296 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4522. Min Range: -6.4522
Max Act: 5.6710. Min Act: -0.1700
Data Index: 5262475 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19