Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 715 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3460. Min Range: -1.3460

Max Act: 1.3460. Min Act: -0.0000

Data Index: 360533 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.3460. Min Range: -1.3460

Max Act: 1.2250. Min Act: -0.0000

Data Index: 180680 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 1.3460. Min Range: -1.3460

Max Act: 1.0887. Min Act: -0.0001

Data Index: 55458 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 1.3460. Min Range: -1.3460

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1127386 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 1.3460. Min Range: -1.3460

Max Act: 1.0938. Min Act: -0.0000

Data Index: 273962 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1358623 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9953. Min Act: -0.0001

Data Index: 1258284 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9570. Min Act: -0.0001

Data Index: 908425 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 1.3460. Min Range: -1.3460

Max Act: 1.0112. Min Act: -0.0000

Data Index: 46732 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1246638 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9593. Min Act: -0.0000

Data Index: 910111 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.8918. Min Act: -0.0001

Data Index: 1260704 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9521. Min Act: -0.0000

Data Index: 1343864 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9838. Min Act: -0.0000

Data Index: 852761 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9499. Min Act: -0.0001

Data Index: 787499 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9199. Min Act: -0.0001

Data Index: 1003119 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9092. Min Act: -0.0001

Data Index: 1329563 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.8860. Min Act: -0.0001

Data Index: 654607 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9076. Min Act: -0.0000

Data Index: 35230 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 1.3460. Min Range: -1.3460

Max Act: 0.9366. Min Act: -0.0000

Data Index: 915831 (C4 (Web Text))

Max Activating Token Index: 761