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

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

Neuron 1538 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: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0000

Data Index: 1120936 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0446. Min Act: -0.0000

Data Index: 908835 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0393. Min Act: -0.0000

Data Index: 73035 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0397. Min Act: -0.0000

Data Index: 415481 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0396. Min Act: -0.0000

Data Index: 1143716 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0371. Min Act: -0.0000

Data Index: 543581 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1187388 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0372. Min Act: -0.0000

Data Index: 831605 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0386. Min Act: -0.0000

Data Index: 106013 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0347. Min Act: -0.0000

Data Index: 513238 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1129551 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0367. Min Act: -0.0000

Data Index: 589748 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0364. Min Act: -0.0000

Data Index: 626399 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0339. Min Act: -0.0000

Data Index: 701887 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0340. Min Act: -0.0000

Data Index: 949294 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0327. Min Act: -0.0000

Data Index: 156914 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0320. Min Act: -0.0000

Data Index: 326257 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1274270 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1000513 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0335. Min Act: -0.0000

Data Index: 293632 (C4 (Web Text))

Max Activating Token Index: 82