Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.9761. Min Act: -0.1700
Data Index: 8405317 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.8199. Min Act: -0.1700
Data Index: 2812069 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.7574. Min Act: -0.1700
Data Index: 5326612 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.7574. Min Act: -0.1700
Data Index: 1922576 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.6949. Min Act: -0.1700
Data Index: 7795024 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.6636. Min Act: -0.1700
Data Index: 501305 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.6636. Min Act: -0.1700
Data Index: 7680554 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.6636. Min Act: -0.1700
Data Index: 5457197 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.6636. Min Act: -0.1700
Data Index: 2223368 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.6636. Min Act: -0.1700
Data Index: 7098764 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.6636. Min Act: -0.1700
Data Index: 736054 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.6636. Min Act: -0.1700
Data Index: 7905190 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.6011. Min Act: -0.1700
Data Index: 7686889 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.6011. Min Act: -0.1700
Data Index: 5516409 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.6011. Min Act: -0.1700
Data Index: 4863311 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.5699. Min Act: -0.1700
Data Index: 8083085 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.5699. Min Act: -0.1700
Data Index: 2147547 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.5386. Min Act: -0.1700
Data Index: 601163 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.5386. Min Act: -0.1700
Data Index: 6651822 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9761. Min Range: -6.9761
Max Act: 6.5074. Min Act: -0.1700
Data Index: 6436372 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19