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

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

Neuron 4984 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1123561 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2191. Min Act: -0.0001

Data Index: 414264 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2167. Min Act: -0.0001

Data Index: 392043 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2200. Min Act: -0.0001

Data Index: 397345 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1193632 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1757. Min Act: -0.0001

Data Index: 918827 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1880. Min Act: -0.0000

Data Index: 895145 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1365. Min Act: -0.0001

Data Index: 435146 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1674. Min Act: -0.0001

Data Index: 710479 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1530. Min Act: -0.0001

Data Index: 36128 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1596553 (Python Code)

Max Activating Token Index: 705

Text #11

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1475. Min Act: -0.0000

Data Index: 583873 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1258131 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1423. Min Act: -0.0001

Data Index: 314325 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1496689 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1442. Min Act: -0.0001

Data Index: 865804 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1383. Min Act: -0.0001

Data Index: 529697 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1468. Min Act: -0.0001

Data Index: 261502 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1334. Min Act: -0.0001

Data Index: 906448 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1375. Min Act: -0.0001

Data Index: 527166 (C4 (Web Text))

Max Activating Token Index: 807