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

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

Neuron 4720 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5626. Min Act: -0.0001

Data Index: 313762 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5726. Min Act: -0.0001

Data Index: 1085536 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5710. Min Act: -0.0001

Data Index: 957152 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6068. Min Act: -0.0001

Data Index: 1248345 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5860. Min Act: -0.0001

Data Index: 239297 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5579. Min Act: -0.0001

Data Index: 887495 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5948. Min Act: -0.0001

Data Index: 987450 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6334. Min Act: -0.0001

Data Index: 1481381 (Python Code)

Max Activating Token Index: 106

Text #8

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6044. Min Act: -0.0001

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5953. Min Act: -0.0001

Data Index: 906735 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5623. Min Act: -0.0001

Data Index: 727151 (C4 (Web Text))

Max Activating Token Index: 415

Text #11

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1161653 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.6150. Min Act: -0.0001

Data Index: 436026 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5773. Min Act: -0.0001

Data Index: 941557 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5379. Min Act: -0.0001

Data Index: 454763 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5425. Min Act: -0.0001

Data Index: 1294398 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5405. Min Act: -0.0001

Data Index: 879079 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.4868. Min Act: -0.0001

Data Index: 147088 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5547. Min Act: -0.0001

Data Index: 164179 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.6334. Min Range: -0.6334

Max Act: 0.5239. Min Act: -0.0001

Data Index: 824811 (C4 (Web Text))

Max Activating Token Index: 479