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

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

Neuron 4003 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6784. Min Range: -5.6784

Max Act: 5.6784. Min Act: -0.0000

Data Index: 444666 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 5.6784. Min Range: -5.6784

Max Act: 5.4712. Min Act: -0.0000

Data Index: 1004835 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 5.6784. Min Range: -5.6784

Max Act: 5.4283. Min Act: -0.0000

Data Index: 772555 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 5.6784. Min Range: -5.6784

Max Act: 5.3771. Min Act: -0.0000

Data Index: 1358951 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 5.6784. Min Range: -5.6784

Max Act: 5.0448. Min Act: -0.0000

Data Index: 771161 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.5386. Min Act: -0.0000

Data Index: 1013308 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.5043. Min Act: -0.0000

Data Index: 1134956 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.2304. Min Act: -0.0000

Data Index: 1314365 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.2964. Min Act: -0.0000

Data Index: 181909 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.2294. Min Act: -0.0000

Data Index: 349567 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.2568. Min Act: -0.0000

Data Index: 256383 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.2236. Min Act: -0.0000

Data Index: 1091140 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.4215. Min Act: -0.0000

Data Index: 52876 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.2117. Min Act: -0.0000

Data Index: 555335 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.3993. Min Act: -0.0000

Data Index: 1202858 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 5.6784. Min Range: -5.6784

Max Act: 3.9951. Min Act: -0.0000

Data Index: 770470 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.5629. Min Act: -0.0000

Data Index: 760681 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 5.6784. Min Range: -5.6784

Max Act: 3.8252. Min Act: -0.0000

Data Index: 423600 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 5.6784. Min Range: -5.6784

Max Act: 4.1238. Min Act: -0.0000

Data Index: 1239536 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 5.6784. Min Range: -5.6784

Max Act: 3.9079. Min Act: -0.0000

Data Index: 607857 (C4 (Web Text))

Max Activating Token Index: 748