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

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

Neuron 3007 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: 0.4481. Min Range: -0.4481

Max Act: 0.4471. Min Act: -0.0000

Data Index: 232466 (C4 (Web Text))

Max Activating Token Index: 617

Text #1

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.4362. Min Act: -0.0000

Data Index: 216585 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.4371. Min Act: -0.0000

Data Index: 128875 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1044756 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1000845 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.4481. Min Act: -0.0000

Data Index: 913261 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3694. Min Act: -0.0000

Data Index: 913510 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1082638 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3936. Min Act: -0.0000

Data Index: 351168 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3886. Min Act: -0.0000

Data Index: 274744 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1108605 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1025264 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3785. Min Act: -0.0000

Data Index: 166063 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3394. Min Act: -0.0000

Data Index: 606421 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3595. Min Act: -0.0000

Data Index: 405565 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3464. Min Act: -0.0000

Data Index: 19916 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3518. Min Act: -0.0000

Data Index: 936455 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3366. Min Act: -0.0000

Data Index: 266355 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3446. Min Act: -0.0000

Data Index: 460754 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.4481. Min Range: -0.4481

Max Act: 0.3267. Min Act: -0.0000

Data Index: 469628 (C4 (Web Text))

Max Activating Token Index: 993