Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 182 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.4776. Min Act: -0.1700
Data Index: 2311443 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.5089. Min Act: -0.1700
Data Index: 2697832 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.4464. Min Act: -0.1700
Data Index: 2059189 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.4151. Min Act: -0.1700
Data Index: 372571 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.4151. Min Act: -0.1700
Data Index: 5021410 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 459486 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 519172 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 15064 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 367780 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 205503 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 612078 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 566027 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 396808 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 599489 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 626892 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 222124 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 593182 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 454166 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 468817 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5089. Min Range: -5.5089
Max Act: 5.3526. Min Act: -0.1700
Data Index: 468813 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19