Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5457 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6385. Min Act: -0.0000

Data Index: 1601531 (Python Code)

Max Activating Token Index: 237

Text #1

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6404. Min Act: -0.0000

Data Index: 227819 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6532. Min Act: -0.0000

Data Index: 441671 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6411. Min Act: -0.0000

Data Index: 774523 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6254. Min Act: -0.0000

Data Index: 99252 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6485. Min Act: -0.0000

Data Index: 320185 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1111684 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5990. Min Act: -0.0000

Data Index: 707362 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1313205 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5945. Min Act: -0.0000

Data Index: 962543 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1006892 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6289. Min Act: -0.0000

Data Index: 888072 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6055. Min Act: -0.0000

Data Index: 809194 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6023. Min Act: -0.0000

Data Index: 428191 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.6336. Min Act: -0.0000

Data Index: 1276237 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1654567 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5992. Min Act: -0.0000

Data Index: 910707 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5659. Min Act: -0.0000

Data Index: 989181 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5813. Min Act: -0.0000

Data Index: 947351 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 0.6532. Min Range: -0.6532

Max Act: 0.5821. Min Act: -0.0000

Data Index: 972751 (C4 (Web Text))

Max Activating Token Index: 405