Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2655 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2570. Min Range: -1.2570

Max Act: 1.2570. Min Act: -0.0000

Data Index: 362313 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.9304. Min Act: -0.0000

Data Index: 805801 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 1.2570. Min Range: -1.2570

Max Act: 1.0828. Min Act: -0.0000

Data Index: 679725 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.7907. Min Act: -0.0000

Data Index: 413855 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.6484. Min Act: -0.0000

Data Index: 1195402 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.6464. Min Act: -0.0000

Data Index: 247702 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.5469. Min Act: -0.0000

Data Index: 587855 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.6053. Min Act: 0.0000

Data Index: 845760 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1121040 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.4722. Min Act: 0.0000

Data Index: 1522607 (Python Code)

Max Activating Token Index: 252

Text #10

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.4538. Min Act: 0.0000

Data Index: 1643383 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.4521. Min Act: -0.0000

Data Index: 107786 (C4 (Web Text))

Max Activating Token Index: 1001

Text #12

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1631021 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1260322 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1500621 (Python Code)

Max Activating Token Index: 437

Text #15

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1447682 (Python Code)

Max Activating Token Index: 945

Text #16

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.4003. Min Act: -0.0000

Data Index: 12411 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.3565. Min Act: -0.0000

Data Index: 737153 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.3609. Min Act: -0.0000

Data Index: 436225 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 1.2570. Min Range: -1.2570

Max Act: 0.3458. Min Act: 0.0000

Data Index: 1601472 (Python Code)

Max Activating Token Index: 73