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

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

Neuron 1380 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.5033. Min Act: -0.0001

Data Index: 970676 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4559. Min Act: -0.0001

Data Index: 1246204 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.4000. Min Act: -0.0001

Data Index: 1230745 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3925. Min Act: -0.0001

Data Index: 1241032 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3255. Min Act: -0.0001

Data Index: 557116 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3094. Min Act: -0.0001

Data Index: 396986 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3062. Min Act: -0.0001

Data Index: 533086 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2889. Min Act: -0.0001

Data Index: 964121 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.3157. Min Act: -0.0000

Data Index: 845465 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2452. Min Act: -0.0001

Data Index: 184349 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2560. Min Act: -0.0001

Data Index: 736001 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2424. Min Act: -0.0001

Data Index: 1037876 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2700. Min Act: -0.0001

Data Index: 339662 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2434. Min Act: -0.0001

Data Index: 231337 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2441. Min Act: -0.0000

Data Index: 261942 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2477. Min Act: -0.0001

Data Index: 1030943 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2634. Min Act: -0.0001

Data Index: 1020661 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2674. Min Act: -0.0001

Data Index: 1010388 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2387. Min Act: -0.0001

Data Index: 996319 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.5033. Min Range: -0.5033

Max Act: 0.2319. Min Act: -0.0001

Data Index: 1126095 (C4 (Web Text))

Max Activating Token Index: 354