Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3083 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.2279. Min Range: -2.2279
Max Act: 2.1280. Min Act: -0.0000
Data Index: 856021 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2279. Min Range: -2.2279
Max Act: 2.2279. Min Act: -0.0000
Data Index: 776870 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2279. Min Range: -2.2279
Max Act: 2.0401. Min Act: -0.0000
Data Index: 201114 (The Pile)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.8824. Min Act: -0.0000
Data Index: 1842351 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2279. Min Range: -2.2279
Max Act: 2.0614. Min Act: -0.0000
Data Index: 1810583 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.7345. Min Act: -0.0000
Data Index: 1789017 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.8451. Min Act: -0.0000
Data Index: 521535 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.9357. Min Act: -0.0000
Data Index: 1638773 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.9280. Min Act: -0.0000
Data Index: 1797667 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.7015. Min Act: -0.0000
Data Index: 75135 (The Pile)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.8010. Min Act: -0.0000
Data Index: 480901 (The Pile)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.7852. Min Act: -0.0000
Data Index: 1231702 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.6842. Min Act: -0.0000
Data Index: 675319 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.8619. Min Act: -0.0000
Data Index: 504042 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.7300. Min Act: -0.0000
Data Index: 1081819 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.8469. Min Act: -0.0000
Data Index: 1231111 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.5363. Min Act: -0.0000
Data Index: 120333 (The Pile)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.7041. Min Act: -0.0000
Data Index: 985102 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.7049. Min Act: -0.0000
Data Index: 1714606 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2279. Min Range: -2.2279
Max Act: 1.6100. Min Act: -0.0000
Data Index: 575666 (The Pile)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19