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

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

Neuron 1106 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0510. Min Act: -0.0005

Data Index: 198752 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0524. Min Act: -0.0005

Data Index: 145872 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0498. Min Act: -0.0005

Data Index: 367560 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0485. Min Act: -0.0005

Data Index: 557853 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0493. Min Act: -0.0005

Data Index: 970730 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0458. Min Act: -0.0005

Data Index: 91686 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0511. Min Act: -0.0005

Data Index: 1358816 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0462. Min Act: -0.0005

Data Index: 966385 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0463. Min Act: -0.0005

Data Index: 1184912 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0443. Min Act: -0.0005

Data Index: 122756 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0451. Min Act: -0.0005

Data Index: 1075771 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0441. Min Act: -0.0005

Data Index: 502729 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0418. Min Act: -0.0005

Data Index: 358413 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0425. Min Act: -0.0005

Data Index: 203196 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0460. Min Act: -0.0005

Data Index: 543670 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0446. Min Act: -0.0005

Data Index: 465269 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0470. Min Act: -0.0005

Data Index: 435739 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0437. Min Act: -0.0005

Data Index: 262682 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0436. Min Act: -0.0005

Data Index: 1306832 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0428. Min Act: -0.0005

Data Index: 140365 (C4 (Web Text))

Max Activating Token Index: 15