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

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

Neuron 617 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: 1.9472. Min Range: -1.9472

Max Act: 1.9472. Min Act: -0.0000

Data Index: 1276819 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.9342. Min Act: -0.0000

Data Index: 1314924 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.7214. Min Act: -0.0000

Data Index: 372114 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.6371. Min Act: -0.0000

Data Index: 478719 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.5471. Min Act: -0.0000

Data Index: 723706 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.4215. Min Act: -0.0000

Data Index: 739177 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.3399. Min Act: -0.0000

Data Index: 914985 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.4209. Min Act: -0.0000

Data Index: 1088615 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.3518. Min Act: -0.0000

Data Index: 461874 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.1943. Min Act: -0.0000

Data Index: 1100986 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.2985. Min Act: -0.0000

Data Index: 824561 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.4549. Min Act: -0.0000

Data Index: 682564 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.3599. Min Act: -0.0000

Data Index: 764787 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.2352. Min Act: -0.0000

Data Index: 861444 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.4218. Min Act: -0.0000

Data Index: 268262 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.3866. Min Act: -0.0000

Data Index: 1021018 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.3914. Min Act: -0.0000

Data Index: 1059716 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.2350. Min Act: -0.0000

Data Index: 1025042 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.2639. Min Act: -0.0000

Data Index: 891452 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 1.9472. Min Range: -1.9472

Max Act: 1.2479. Min Act: -0.0000

Data Index: 880165 (C4 (Web Text))

Max Activating Token Index: 992