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

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

Neuron 4797 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.4430. Min Act: -0.0000

Data Index: 199947 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.3486. Min Act: -0.0000

Data Index: 829936 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.3668. Min Act: -0.0000

Data Index: 702557 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.3174. Min Act: -0.0000

Data Index: 8026 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.3135. Min Act: -0.0000

Data Index: 1262232 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.2848. Min Act: -0.0000

Data Index: 1186707 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.3099. Min Act: -0.0000

Data Index: 114943 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.3033. Min Act: -0.0000

Data Index: 839065 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.3428. Min Act: -0.0000

Data Index: 529498 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.2857. Min Act: -0.0000

Data Index: 352255 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.2586. Min Act: -0.0000

Data Index: 244829 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.2533. Min Act: -0.0000

Data Index: 891910 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1156877 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.2786. Min Act: -0.0000

Data Index: 81645 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1964. Min Act: -0.0000

Data Index: 640800 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1902. Min Act: -0.0000

Data Index: 617634 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1818. Min Act: -0.0000

Data Index: 820633 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.2158. Min Act: -0.0000

Data Index: 368584 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.2099. Min Act: -0.0000

Data Index: 460443 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.2454. Min Act: -0.0000

Data Index: 538828 (C4 (Web Text))

Max Activating Token Index: 880