Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 303 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2881. Min Act: -0.0001

Data Index: 184400 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2900. Min Act: -0.0001

Data Index: 475550 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2819. Min Act: -0.0001

Data Index: 580787 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2617. Min Act: 0.0000

Data Index: 92478 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2339. Min Act: 0.0000

Data Index: 1152702 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2584. Min Act: -0.0001

Data Index: 1238802 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2367. Min Act: -0.0001

Data Index: 500817 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2553. Min Act: -0.0001

Data Index: 1252344 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2476. Min Act: -0.0001

Data Index: 175369 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2568. Min Act: -0.0001

Data Index: 698733 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2393. Min Act: -0.0000

Data Index: 681002 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2546. Min Act: -0.0001

Data Index: 1027010 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2443. Min Act: -0.0001

Data Index: 97856 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2420. Min Act: -0.0001

Data Index: 996736 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1007356 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2372. Min Act: -0.0001

Data Index: 235945 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2461. Min Act: -0.0001

Data Index: 1228182 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2443. Min Act: -0.0001

Data Index: 863204 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2374. Min Act: -0.0001

Data Index: 356158 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2426. Min Act: -0.0001

Data Index: 103119 (C4 (Web Text))

Max Activating Token Index: 742