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

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

Neuron 6039 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: 2.3364. Min Range: -2.3364

Max Act: 2.3364. Min Act: -0.0000

Data Index: 1535954 (Python Code)

Max Activating Token Index: 995

Text #1

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.6193. Min Act: -0.0000

Data Index: 1307549 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.9760. Min Act: -0.0000

Data Index: 1499308 (Python Code)

Max Activating Token Index: 198

Text #3

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.8031. Min Act: -0.0000

Data Index: 1594246 (Python Code)

Max Activating Token Index: 222

Text #4

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.5166. Min Act: -0.0000

Data Index: 1413955 (Python Code)

Max Activating Token Index: 420

Text #5

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.4785. Min Act: -0.0000

Data Index: 1400578 (Python Code)

Max Activating Token Index: 196

Text #6

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.5136. Min Act: -0.0000

Data Index: 657150 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.5976. Min Act: -0.0000

Data Index: 566766 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.5970. Min Act: -0.0000

Data Index: 1020586 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.4365. Min Act: -0.0000

Data Index: 714416 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.4276. Min Act: -0.0000

Data Index: 44457 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.3180. Min Act: -0.0000

Data Index: 1419736 (Python Code)

Max Activating Token Index: 404

Text #12

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.3794. Min Act: -0.0000

Data Index: 1482618 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.3852. Min Act: -0.0000

Data Index: 1366001 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1444796 (Python Code)

Max Activating Token Index: 199

Text #15

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.2258. Min Act: -0.0000

Data Index: 1456195 (Python Code)

Max Activating Token Index: 421

Text #16

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.2868. Min Act: -0.0000

Data Index: 1636668 (Python Code)

Max Activating Token Index: 501

Text #17

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.3262. Min Act: -0.0000

Data Index: 627085 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.2648. Min Act: -0.0000

Data Index: 1582291 (Python Code)

Max Activating Token Index: 869

Text #19

Max Range: 2.3364. Min Range: -2.3364

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1120150 (C4 (Web Text))

Max Activating Token Index: 549