Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1743 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.9232. Min Act: -0.1700
Data Index: 669646 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.7669. Min Act: -0.1700
Data Index: 3250174 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.7669. Min Act: -0.1700
Data Index: 93653 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.7043. Min Act: -0.1700
Data Index: 2093849 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.7356. Min Act: -0.1700
Data Index: 180499 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.7043. Min Act: -0.1700
Data Index: 180498 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.7043. Min Act: -0.1700
Data Index: 8222253 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.6417. Min Act: -0.1700
Data Index: 4520207 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.6417. Min Act: -0.1700
Data Index: 3730694 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.6104. Min Act: -0.1700
Data Index: 5675487 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.6417. Min Act: -0.1700
Data Index: 8276407 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.6104. Min Act: -0.1700
Data Index: 4066070 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.6730. Min Act: -0.1700
Data Index: 5949561 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.6104. Min Act: -0.1700
Data Index: 669645 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.5791. Min Act: -0.1700
Data Index: 669647 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.5478. Min Act: -0.1700
Data Index: 7033731 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.5791. Min Act: -0.1700
Data Index: 180497 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.5478. Min Act: -0.1700
Data Index: 7767521 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.6417. Min Act: -0.1700
Data Index: 2293121 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9232. Min Range: -3.9232
Max Act: 3.5478. Min Act: -0.1700
Data Index: 4993568 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19