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

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

Neuron 5985 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.5192. Min Act: -0.0001

Data Index: 1473415 (Python Code)

Max Activating Token Index: 203

Text #1

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4397. Min Act: -0.0001

Data Index: 72105 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4233. Min Act: -0.0001

Data Index: 4583 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4125. Min Act: -0.0001

Data Index: 1499480 (Python Code)

Max Activating Token Index: 793

Text #4

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.4041. Min Act: -0.0001

Data Index: 48802 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3814. Min Act: -0.0001

Data Index: 1477250 (Python Code)

Max Activating Token Index: 548

Text #6

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3744. Min Act: -0.0001

Data Index: 1371553 (Python Code)

Max Activating Token Index: 572

Text #7

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3693. Min Act: -0.0001

Data Index: 1501258 (Python Code)

Max Activating Token Index: 66

Text #8

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3669. Min Act: -0.0001

Data Index: 579962 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3520. Min Act: -0.0001

Data Index: 485862 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3501. Min Act: -0.0001

Data Index: 1397896 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3367. Min Act: -0.0001

Data Index: 1538319 (Python Code)

Max Activating Token Index: 402

Text #12

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3415. Min Act: -0.0001

Data Index: 1618399 (Python Code)

Max Activating Token Index: 948

Text #13

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3205. Min Act: -0.0001

Data Index: 1441665 (Python Code)

Max Activating Token Index: 501

Text #14

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3243. Min Act: -0.0002

Data Index: 1424348 (Python Code)

Max Activating Token Index: 593

Text #15

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3228. Min Act: -0.0001

Data Index: 1063442 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3278. Min Act: -0.0001

Data Index: 34848 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3247. Min Act: -0.0002

Data Index: 1461066 (Python Code)

Max Activating Token Index: 566

Text #18

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3254. Min Act: -0.0001

Data Index: 1562726 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 0.5192. Min Range: -0.5192

Max Act: 0.3166. Min Act: -0.0001

Data Index: 1471918 (Python Code)

Max Activating Token Index: 41