Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4297 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0002

Data Index: 677949 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0533. Min Act: -0.0002

Data Index: 110043 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0547. Min Act: -0.0002

Data Index: 747646 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0534. Min Act: -0.0002

Data Index: 37985 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1167458 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1291657 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0523. Min Act: -0.0002

Data Index: 76620 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0513. Min Act: -0.0002

Data Index: 879033 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0514. Min Act: -0.0002

Data Index: 302657 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0511. Min Act: -0.0002

Data Index: 75567 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0525. Min Act: -0.0002

Data Index: 697851 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0486. Min Act: -0.0002

Data Index: 657235 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0521. Min Act: -0.0002

Data Index: 883599 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1004284 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1299033 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0512. Min Act: -0.0002

Data Index: 94082 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1096786 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0485. Min Act: -0.0002

Data Index: 966407 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0475. Min Act: -0.0002

Data Index: 623209 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0524. Min Act: -0.0002

Data Index: 896242 (C4 (Web Text))

Max Activating Token Index: 111