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

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

Neuron 4000 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.9732. Min Act: -0.0000

Data Index: 42459 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.9343. Min Act: -0.0000

Data Index: 863389 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.8228. Min Act: -0.0000

Data Index: 405364 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.6331. Min Act: -0.0000

Data Index: 817212 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.7102. Min Act: -0.0000

Data Index: 293233 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.7861. Min Act: -0.0000

Data Index: 122989 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.5034. Min Act: -0.0000

Data Index: 796254 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.4563. Min Act: -0.0000

Data Index: 1494591 (Python Code)

Max Activating Token Index: 161

Text #8

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.4534. Min Act: -0.0000

Data Index: 160072 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.4424. Min Act: -0.0000

Data Index: 978777 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.4269. Min Act: -0.0000

Data Index: 1136131 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.4855. Min Act: -0.0000

Data Index: 615051 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.3778. Min Act: -0.0000

Data Index: 1329764 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.4557. Min Act: -0.0000

Data Index: 988193 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.4465. Min Act: -0.0000

Data Index: 826501 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.3724. Min Act: -0.0000

Data Index: 753312 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1349402 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1569663 (Python Code)

Max Activating Token Index: 294

Text #18

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.3191. Min Act: -0.0000

Data Index: 578532 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 1.9732. Min Range: -1.9732

Max Act: 1.3647. Min Act: -0.0000

Data Index: 131994 (C4 (Web Text))

Max Activating Token Index: 371