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

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

Neuron 832 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3643. Min Range: -6.3643

Max Act: 6.3619. Min Act: -0.0000

Data Index: 1091943 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 6.3643. Min Range: -6.3643

Max Act: 6.2927. Min Act: -0.0000

Data Index: 374321 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 6.3643. Min Range: -6.3643

Max Act: 6.3643. Min Act: -0.0000

Data Index: 18428 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 6.3643. Min Range: -6.3643

Max Act: 6.0378. Min Act: -0.0000

Data Index: 614622 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.9366. Min Act: -0.0000

Data Index: 716135 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.7069. Min Act: -0.0000

Data Index: 215492 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 6.3643. Min Range: -6.3643

Max Act: 5.9090. Min Act: -0.0000

Data Index: 1330565 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.7762. Min Act: -0.0000

Data Index: 732838 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.9220. Min Act: -0.0000

Data Index: 636199 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.7041. Min Act: -0.0000

Data Index: 980463 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.4570. Min Act: -0.0000

Data Index: 435412 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.4970. Min Act: -0.0000

Data Index: 1140707 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.5008. Min Act: -0.0000

Data Index: 431562 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.2583. Min Act: -0.0000

Data Index: 586436 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.4561. Min Act: -0.0000

Data Index: 697378 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.1179. Min Act: -0.0000

Data Index: 1237352 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.2773. Min Act: -0.0000

Data Index: 338272 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 6.3643. Min Range: -6.3643

Max Act: 4.0933. Min Act: -0.0000

Data Index: 913421 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 6.3643. Min Range: -6.3643

Max Act: 3.9833. Min Act: -0.0000

Data Index: 477213 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 6.3643. Min Range: -6.3643

Max Act: 3.9634. Min Act: -0.0000

Data Index: 422463 (C4 (Web Text))

Max Activating Token Index: 491