Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3578 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.8515. Min Act: -0.0001

Data Index: 698766 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.7238. Min Act: -0.0001

Data Index: 640073 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.7045. Min Act: -0.0001

Data Index: 482779 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.7494. Min Act: -0.0001

Data Index: 1333843 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.7022. Min Act: -0.0001

Data Index: 1131969 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6543. Min Act: -0.0001

Data Index: 247456 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6259. Min Act: -0.0001

Data Index: 139741 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6759. Min Act: -0.0001

Data Index: 303997 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6661. Min Act: -0.0001

Data Index: 1519857 (Python Code)

Max Activating Token Index: 303

Text #9

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6980. Min Act: -0.0001

Data Index: 339952 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.7005. Min Act: -0.0001

Data Index: 46007 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6269. Min Act: -0.0001

Data Index: 1232242 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6204. Min Act: -0.0001

Data Index: 1305110 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6814. Min Act: -0.0001

Data Index: 756320 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6123. Min Act: -0.0001

Data Index: 158448 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6119. Min Act: -0.0001

Data Index: 1014278 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.5957. Min Act: -0.0001

Data Index: 211298 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.5615. Min Act: -0.0001

Data Index: 760173 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6328. Min Act: -0.0001

Data Index: 923188 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.8515. Min Range: -0.8515

Max Act: 0.6306. Min Act: -0.0001

Data Index: 267211 (C4 (Web Text))

Max Activating Token Index: 58