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

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

Neuron 1828 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: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1228839 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0551. Min Act: -0.0001

Data Index: 989264 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0509. Min Act: -0.0002

Data Index: 847929 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1163203 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0488. Min Act: -0.0002

Data Index: 823775 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0487. Min Act: -0.0002

Data Index: 754926 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0487. Min Act: -0.0002

Data Index: 928391 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0485. Min Act: -0.0002

Data Index: 890434 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0474. Min Act: -0.0002

Data Index: 980945 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0487. Min Act: -0.0001

Data Index: 1180021 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0461. Min Act: -0.0002

Data Index: 484694 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0475. Min Act: -0.0002

Data Index: 603855 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1071822 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0463. Min Act: -0.0002

Data Index: 887157 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0455. Min Act: -0.0002

Data Index: 279676 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1177484 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0460. Min Act: -0.0001

Data Index: 4197 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1358725 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0458. Min Act: -0.0001

Data Index: 159924 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0462. Min Act: -0.0001

Data Index: 96722 (C4 (Web Text))

Max Activating Token Index: 452