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

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

Neuron 4657 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4546. Min Range: -2.4546

Max Act: 2.3824. Min Act: -0.0000

Data Index: 1376376 (Python Code)

Max Activating Token Index: 399

Text #1

Max Range: 2.4546. Min Range: -2.4546

Max Act: 2.1449. Min Act: -0.0001

Data Index: 1544013 (Python Code)

Max Activating Token Index: 899

Text #2

Max Range: 2.4546. Min Range: -2.4546

Max Act: 2.4546. Min Act: -0.0000

Data Index: 1531093 (Python Code)

Max Activating Token Index: 359

Text #3

Max Range: 2.4546. Min Range: -2.4546

Max Act: 2.3423. Min Act: -0.0000

Data Index: 1393852 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 2.4546. Min Range: -2.4546

Max Act: 2.1125. Min Act: -0.0000

Data Index: 1141903 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 2.4546. Min Range: -2.4546

Max Act: 2.1319. Min Act: -0.0000

Data Index: 1501423 (Python Code)

Max Activating Token Index: 127

Text #6

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.9957. Min Act: -0.0000

Data Index: 1506330 (Python Code)

Max Activating Token Index: 78

Text #7

Max Range: 2.4546. Min Range: -2.4546

Max Act: 2.2001. Min Act: -0.0001

Data Index: 737655 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 2.4546. Min Range: -2.4546

Max Act: 2.0181. Min Act: -0.0001

Data Index: 692258 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.7798. Min Act: -0.0001

Data Index: 1100417 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.8299. Min Act: -0.0001

Data Index: 1301556 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.7325. Min Act: -0.0000

Data Index: 529692 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.6089. Min Act: -0.0000

Data Index: 1645066 (Python Code)

Max Activating Token Index: 799

Text #13

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.7945. Min Act: -0.0001

Data Index: 997234 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.6812. Min Act: -0.0000

Data Index: 1290020 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.5034. Min Act: -0.0000

Data Index: 1575003 (Python Code)

Max Activating Token Index: 153

Text #16

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.6367. Min Act: -0.0001

Data Index: 295156 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.6249. Min Act: -0.0000

Data Index: 36998 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.8264. Min Act: -0.0001

Data Index: 1046976 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 2.4546. Min Range: -2.4546

Max Act: 1.8160. Min Act: -0.0001

Data Index: 1031192 (C4 (Web Text))

Max Activating Token Index: 835