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

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

Neuron 4036 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.4332. Min Act: -0.0001

Data Index: 657580 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3278. Min Act: -0.0001

Data Index: 956976 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2345. Min Act: -0.0001

Data Index: 676603 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2127. Min Act: -0.0001

Data Index: 540379 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2823. Min Act: -0.0001

Data Index: 1071399 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.3597. Min Act: -0.0001

Data Index: 383197 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2760. Min Act: -0.0001

Data Index: 955051 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.1818. Min Act: -0.0000

Data Index: 472864 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.2811. Min Act: -0.0001

Data Index: 602277 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.0636. Min Act: -0.0001

Data Index: 816129 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.1731. Min Act: -0.0001

Data Index: 1271995 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.1246. Min Act: -0.0001

Data Index: 113380 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.1537. Min Act: -0.0001

Data Index: 983598 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.1363. Min Act: -0.0001

Data Index: 770761 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.1176. Min Act: -0.0001

Data Index: 1454241 (Python Code)

Max Activating Token Index: 419

Text #15

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.0420. Min Act: -0.0001

Data Index: 1059921 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.0480. Min Act: -0.0001

Data Index: 554054 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.0731. Min Act: -0.0000

Data Index: 941799 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.0621. Min Act: -0.0001

Data Index: 670431 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 1.4332. Min Range: -1.4332

Max Act: 1.0532. Min Act: -0.0001

Data Index: 1565720 (Python Code)

Max Activating Token Index: 410