Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 223 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.6006. Min Act: -0.1700
Data Index: 989398 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.4444. Min Act: -0.1700
Data Index: 6451919 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.4756. Min Act: -0.1700
Data Index: 7832181 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.3506. Min Act: -0.1700
Data Index: 2091864 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.3194. Min Act: -0.1700
Data Index: 6243844 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.2256. Min Act: -0.1700
Data Index: 605159 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.1944. Min Act: -0.1700
Data Index: 4428761 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.1944. Min Act: -0.1700
Data Index: 8719418 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.0694. Min Act: -0.1700
Data Index: 2744539 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.0381. Min Act: -0.1700
Data Index: 580308 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.0069. Min Act: -0.1700
Data Index: 441243 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.0381. Min Act: -0.1700
Data Index: 6588440 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.0069. Min Act: -0.1700
Data Index: 1467915 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.0381. Min Act: -0.1700
Data Index: 7872208 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.0069. Min Act: -0.1700
Data Index: 7836577 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.0069. Min Act: -0.1700
Data Index: 3527861 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6006. Min Range: -6.6006
Max Act: 6.0069. Min Act: -0.1700
Data Index: 7437501 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6006. Min Range: -6.6006
Max Act: 5.9756. Min Act: -0.1700
Data Index: 1922574 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6006. Min Range: -6.6006
Max Act: 5.9756. Min Act: -0.1700
Data Index: 2966745 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6006. Min Range: -6.6006
Max Act: 5.9756. Min Act: -0.1700
Data Index: 565058 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19