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

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

Neuron 3250 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4590. Min Range: -2.4590

Max Act: 2.4590. Min Act: -0.0000

Data Index: 1238995 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 2.4590. Min Range: -2.4590

Max Act: 2.2617. Min Act: -0.0000

Data Index: 219497 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 2.4590. Min Range: -2.4590

Max Act: 2.1522. Min Act: -0.0000

Data Index: 130792 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.9895. Min Act: -0.0000

Data Index: 344137 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 2.4590. Min Range: -2.4590

Max Act: 2.0415. Min Act: -0.0000

Data Index: 449199 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 2.4590. Min Range: -2.4590

Max Act: 2.0312. Min Act: -0.0000

Data Index: 1423148 (Python Code)

Max Activating Token Index: 156

Text #6

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.9323. Min Act: -0.0000

Data Index: 1011011 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.9072. Min Act: -0.0000

Data Index: 1448652 (Python Code)

Max Activating Token Index: 346

Text #8

Max Range: 2.4590. Min Range: -2.4590

Max Act: 2.0950. Min Act: -0.0000

Data Index: 1092706 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.9199. Min Act: -0.0000

Data Index: 1377073 (Python Code)

Max Activating Token Index: 174

Text #10

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.7974. Min Act: -0.0000

Data Index: 508387 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.8742. Min Act: -0.0000

Data Index: 396832 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.5401. Min Act: -0.0000

Data Index: 895001 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.9662. Min Act: -0.0000

Data Index: 71007 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.7594. Min Act: -0.0000

Data Index: 469519 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.7803. Min Act: -0.0000

Data Index: 1495178 (Python Code)

Max Activating Token Index: 977

Text #16

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.7688. Min Act: -0.0000

Data Index: 1562191 (Python Code)

Max Activating Token Index: 999

Text #17

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.7432. Min Act: -0.0000

Data Index: 1582815 (Python Code)

Max Activating Token Index: 793

Text #18

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.7490. Min Act: -0.0000

Data Index: 1491221 (Python Code)

Max Activating Token Index: 1017

Text #19

Max Range: 2.4590. Min Range: -2.4590

Max Act: 1.7439. Min Act: -0.0000

Data Index: 1509614 (Python Code)

Max Activating Token Index: 991