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

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

Neuron 2794 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: 0.0706. Min Range: -0.0706

Max Act: 0.0706. Min Act: -0.0001

Data Index: 588898 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0624. Min Act: -0.0001

Data Index: 782188 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0600. Min Act: -0.0001

Data Index: 990147 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0507. Min Act: -0.0001

Data Index: 741717 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1227689 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0484. Min Act: -0.0001

Data Index: 1305408 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0450. Min Act: -0.0001

Data Index: 112796 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0447. Min Act: -0.0001

Data Index: 770200 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0462. Min Act: -0.0001

Data Index: 244627 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0458. Min Act: -0.0001

Data Index: 651910 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1612246 (Python Code)

Max Activating Token Index: 78

Text #11

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0451. Min Act: -0.0001

Data Index: 267830 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0435. Min Act: -0.0001

Data Index: 517957 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0443. Min Act: -0.0001

Data Index: 534176 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1073551 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0442. Min Act: -0.0001

Data Index: 832668 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1166572 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0414. Min Act: -0.0001

Data Index: 1593129 (Python Code)

Max Activating Token Index: 176

Text #18

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1511460 (Python Code)

Max Activating Token Index: 151

Text #19

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0431. Min Act: -0.0001

Data Index: 623010 (C4 (Web Text))

Max Activating Token Index: 806