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

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

Neuron 3825 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0625. Min Act: -0.0003

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0444. Min Act: -0.0002

Data Index: 879037 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0374. Min Act: -0.0003

Data Index: 703578 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0359. Min Act: -0.0002

Data Index: 641042 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0365. Min Act: -0.0003

Data Index: 794200 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1097305 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0350. Min Act: -0.0003

Data Index: 355270 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0317. Min Act: -0.0003

Data Index: 115394 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0326. Min Act: -0.0003

Data Index: 476828 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1208804 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0308. Min Act: -0.0003

Data Index: 402624 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0309. Min Act: -0.0003

Data Index: 505146 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0302. Min Act: -0.0003

Data Index: 916965 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0308. Min Act: -0.0002

Data Index: 65584 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0305. Min Act: -0.0002

Data Index: 1104974 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0294. Min Act: -0.0002

Data Index: 968050 (C4 (Web Text))

Max Activating Token Index: 594

Text #16

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1255373 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0277. Min Act: -0.0003

Data Index: 645807 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0292. Min Act: -0.0003

Data Index: 832224 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0288. Min Act: -0.0003

Data Index: 827334 (C4 (Web Text))

Max Activating Token Index: 177