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

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

Neuron 2100 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.2655. Min Act: -0.0000

Data Index: 797080 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1201288 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1040165 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7809. Min Act: -0.0000

Data Index: 209526 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.8343. Min Act: -0.0000

Data Index: 918194 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7732. Min Act: -0.0000

Data Index: 175107 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7444. Min Act: -0.0000

Data Index: 17376 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7893. Min Act: -0.0000

Data Index: 578035 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1076734 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7632. Min Act: -0.0000

Data Index: 353565 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7555. Min Act: -0.0000

Data Index: 401438 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7408. Min Act: -0.0000

Data Index: 296526 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7213. Min Act: -0.0000

Data Index: 624087 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.6776. Min Act: -0.0000

Data Index: 763777 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1254631 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.6960. Min Act: -0.0000

Data Index: 666325 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1174327 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.6493. Min Act: -0.0000

Data Index: 837610 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.6933. Min Act: -0.0000

Data Index: 1007478 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 1.2655. Min Range: -1.2655

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1220879 (C4 (Web Text))

Max Activating Token Index: 437