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

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

Neuron 4137 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.4543. Min Act: -0.0001

Data Index: 1325258 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.4439. Min Act: -0.0001

Data Index: 396840 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.4378. Min Act: -0.0001

Data Index: 1142208 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.4123. Min Act: -0.0001

Data Index: 382844 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.4100. Min Act: -0.0001

Data Index: 843889 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3761. Min Act: -0.0001

Data Index: 467256 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3605. Min Act: -0.0001

Data Index: 966576 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3771. Min Act: -0.0001

Data Index: 1634042 (Python Code)

Max Activating Token Index: 316

Text #8

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3556. Min Act: -0.0001

Data Index: 616021 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3477. Min Act: -0.0001

Data Index: 1464802 (Python Code)

Max Activating Token Index: 460

Text #10

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3456. Min Act: -0.0001

Data Index: 1224406 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3537. Min Act: -0.0001

Data Index: 662368 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3527. Min Act: -0.0001

Data Index: 385885 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3436. Min Act: -0.0001

Data Index: 735968 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3492. Min Act: -0.0001

Data Index: 1125814 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3481. Min Act: -0.0001

Data Index: 211168 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3519. Min Act: -0.0001

Data Index: 357576 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3582. Min Act: -0.0001

Data Index: 154393 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3388. Min Act: -0.0001

Data Index: 1072111 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.4543. Min Range: -0.4543

Max Act: 0.3607. Min Act: -0.0001

Data Index: 1243496 (C4 (Web Text))

Max Activating Token Index: 685