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

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

Neuron 1906 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1395. Min Range: -5.1395

Max Act: 5.1395. Min Act: -0.0001

Data Index: 907527 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 5.1395. Min Range: -5.1395

Max Act: 5.0778. Min Act: -0.0001

Data Index: 599631 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.3997. Min Act: -0.0001

Data Index: 1008685 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.0640. Min Act: -0.0001

Data Index: 776683 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.3170. Min Act: -0.0001

Data Index: 198680 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.1613. Min Act: -0.0001

Data Index: 20135 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.3172. Min Act: -0.0001

Data Index: 163929 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.2726. Min Act: -0.0001

Data Index: 964184 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.1400. Min Act: -0.0001

Data Index: 607718 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.3223. Min Act: -0.0001

Data Index: 61454 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.3015. Min Act: -0.0001

Data Index: 664038 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.1780. Min Act: -0.0001

Data Index: 438394 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.2792. Min Act: -0.0001

Data Index: 699141 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.2184. Min Act: -0.0001

Data Index: 229071 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 5.1395. Min Range: -5.1395

Max Act: 3.7349. Min Act: -0.0001

Data Index: 610741 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.0599. Min Act: -0.0001

Data Index: 14487 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.0993. Min Act: -0.0001

Data Index: 438453 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.0362. Min Act: -0.0001

Data Index: 964023 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 5.1395. Min Range: -5.1395

Max Act: 3.2770. Min Act: -0.0001

Data Index: 973526 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 5.1395. Min Range: -5.1395

Max Act: 4.0964. Min Act: -0.0001

Data Index: 608744 (C4 (Web Text))

Max Activating Token Index: 267