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

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

Neuron 1576 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3325. Min Range: -1.3325

Max Act: 1.3325. Min Act: -0.0001

Data Index: 1347438 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 1.3325. Min Range: -1.3325

Max Act: 1.1779. Min Act: -0.0000

Data Index: 903274 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.9503. Min Act: -0.0001

Data Index: 1309683 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.9809. Min Act: -0.0000

Data Index: 289146 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.9240. Min Act: -0.0000

Data Index: 577565 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.8659. Min Act: -0.0000

Data Index: 1021419 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1223605 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.8009. Min Act: -0.0000

Data Index: 27667 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7870. Min Act: -0.0000

Data Index: 458631 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.8534. Min Act: -0.0000

Data Index: 706091 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.8742. Min Act: -0.0000

Data Index: 630716 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1332867 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7714. Min Act: -0.0000

Data Index: 883609 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7547. Min Act: -0.0000

Data Index: 267177 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1264761 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7464. Min Act: -0.0000

Data Index: 733532 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1297720 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7168. Min Act: -0.0000

Data Index: 440588 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7596. Min Act: -0.0000

Data Index: 44774 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 1.3325. Min Range: -1.3325

Max Act: 0.7102. Min Act: -0.0000

Data Index: 917934 (C4 (Web Text))

Max Activating Token Index: 880