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

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

Neuron 3886 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: 0.8705. Min Range: -0.8705

Max Act: 0.8705. Min Act: -0.0000

Data Index: 387734 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.8546. Min Act: -0.0000

Data Index: 313082 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.7383. Min Act: -0.0000

Data Index: 594593 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1171433 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.7313. Min Act: -0.0000

Data Index: 941106 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6980. Min Act: -0.0000

Data Index: 719687 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6909. Min Act: -0.0000

Data Index: 705755 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1180482 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6791. Min Act: -0.0000

Data Index: 51712 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6449. Min Act: -0.0000

Data Index: 421268 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1181517 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1232344 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6044. Min Act: -0.0000

Data Index: 979193 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1112300 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6188. Min Act: -0.0000

Data Index: 400464 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1250245 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6325. Min Act: -0.0000

Data Index: 317402 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6239. Min Act: -0.0000

Data Index: 353104 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.6486. Min Act: -0.0000

Data Index: 995079 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.8705. Min Range: -0.8705

Max Act: 0.5693. Min Act: -0.0000

Data Index: 379191 (C4 (Web Text))

Max Activating Token Index: 175