Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1534 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0572. Min Act: -0.0002

Data Index: 267941 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0538. Min Act: -0.0002

Data Index: 238649 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0543. Min Act: -0.0002

Data Index: 336156 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0523. Min Act: -0.0002

Data Index: 917637 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0540. Min Act: -0.0002

Data Index: 778696 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1168580 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0481. Min Act: -0.0002

Data Index: 267851 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0488. Min Act: -0.0002

Data Index: 634751 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0500. Min Act: -0.0002

Data Index: 418553 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1263163 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0489. Min Act: -0.0002

Data Index: 508758 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0485. Min Act: -0.0002

Data Index: 802569 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0481. Min Act: -0.0002

Data Index: 168846 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1238496 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0481. Min Act: -0.0002

Data Index: 416709 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1181992 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0474. Min Act: -0.0002

Data Index: 127705 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0464. Min Act: -0.0002

Data Index: 111178 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0457. Min Act: -0.0002

Data Index: 641326 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.0572. Min Range: -0.0572

Max Act: 0.0440. Min Act: -0.0002

Data Index: 793600 (C4 (Web Text))

Max Activating Token Index: 980