Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5005 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.9264. Min Act: -0.0000

Data Index: 1353703 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 2.0866. Min Range: -2.0866

Max Act: 2.0866. Min Act: -0.0000

Data Index: 1598513 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.6451. Min Act: -0.0000

Data Index: 1451475 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 2.0866. Min Range: -2.0866

Max Act: 2.0378. Min Act: -0.0000

Data Index: 232016 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1618065 (Python Code)

Max Activating Token Index: 198

Text #5

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.8878. Min Act: -0.0000

Data Index: 1543370 (Python Code)

Max Activating Token Index: 298

Text #6

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.5730. Min Act: -0.0000

Data Index: 347938 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.5859. Min Act: -0.0000

Data Index: 641432 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.5610. Min Act: -0.0000

Data Index: 1497946 (Python Code)

Max Activating Token Index: 256

Text #9

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.8167. Min Act: -0.0000

Data Index: 1605536 (Python Code)

Max Activating Token Index: 711

Text #10

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.7611. Min Act: -0.0000

Data Index: 298695 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1232007 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.5154. Min Act: -0.0000

Data Index: 1585620 (Python Code)

Max Activating Token Index: 587

Text #13

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.4335. Min Act: -0.0000

Data Index: 304584 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.4960. Min Act: -0.0000

Data Index: 842298 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.5323. Min Act: -0.0000

Data Index: 1075146 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.3547. Min Act: -0.0000

Data Index: 1472360 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.6872. Min Act: -0.0000

Data Index: 694339 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.3619. Min Act: -0.0000

Data Index: 12602 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 2.0866. Min Range: -2.0866

Max Act: 1.2797. Min Act: -0.0000

Data Index: 261774 (C4 (Web Text))

Max Activating Token Index: 709