Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 984 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.5867. Min Act: -0.1700
Data Index: 2934919 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.5553. Min Act: -0.1700
Data Index: 5263432 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.5397. Min Act: -0.1700
Data Index: 1811454 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.5397. Min Act: -0.1700
Data Index: 3833767 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.5240. Min Act: -0.1700
Data Index: 111427 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.5240. Min Act: -0.1700
Data Index: 1371218 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4927. Min Act: -0.1700
Data Index: 162363 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4614. Min Act: -0.1700
Data Index: 7926774 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4614. Min Act: -0.1700
Data Index: 2533157 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4614. Min Act: -0.1700
Data Index: 180184 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4457. Min Act: -0.1700
Data Index: 6237826 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4457. Min Act: -0.1700
Data Index: 28625 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4144. Min Act: -0.1700
Data Index: 8097165 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4457. Min Act: -0.1700
Data Index: 1017425 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4144. Min Act: -0.1700
Data Index: 8287186 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4144. Min Act: -0.1700
Data Index: 799532 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4144. Min Act: -0.1700
Data Index: 863918 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4300. Min Act: -0.1700
Data Index: 4553215 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4144. Min Act: -0.1700
Data Index: 5295122 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5867. Min Range: -3.5867
Max Act: 3.4144. Min Act: -0.1700
Data Index: 5505565 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19