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

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

Neuron 3542 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.6557. Min Act: 0.0000

Data Index: 1260705 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5642. Min Act: 0.0000

Data Index: 332035 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1078228 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5396. Min Act: -0.0000

Data Index: 836766 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1087666 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5190. Min Act: -0.0000

Data Index: 890533 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5321. Min Act: -0.0000

Data Index: 610189 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5043. Min Act: 0.0000

Data Index: 295577 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1325683 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5029. Min Act: 0.0000

Data Index: 59253 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4560. Min Act: -0.0000

Data Index: 906957 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4714. Min Act: -0.0000

Data Index: 227293 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4848. Min Act: 0.0000

Data Index: 1029636 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4609. Min Act: -0.0000

Data Index: 370946 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4616. Min Act: 0.0000

Data Index: 198267 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4221. Min Act: -0.0000

Data Index: 470396 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4725. Min Act: -0.0000

Data Index: 59596 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1044312 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4442. Min Act: -0.0000

Data Index: 841227 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4568. Min Act: -0.0000

Data Index: 36631 (C4 (Web Text))

Max Activating Token Index: 998