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

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

Neuron 537 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1647. Min Act: -0.0001

Data Index: 1043765 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1495. Min Act: -0.0001

Data Index: 849422 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1411. Min Act: -0.0001

Data Index: 561313 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1499. Min Act: -0.0001

Data Index: 693668 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1185441 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1245. Min Act: -0.0001

Data Index: 24028 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1304. Min Act: -0.0001

Data Index: 358158 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1255350 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1199679 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1219. Min Act: -0.0001

Data Index: 694117 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1185. Min Act: -0.0001

Data Index: 720396 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1524194 (Python Code)

Max Activating Token Index: 320

Text #12

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1250. Min Act: -0.0001

Data Index: 79831 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1182. Min Act: -0.0001

Data Index: 510376 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1104218 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.0929. Min Act: -0.0001

Data Index: 108673 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1042. Min Act: -0.0001

Data Index: 995417 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1154. Min Act: -0.0001

Data Index: 901056 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1124. Min Act: -0.0001

Data Index: 258274 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.1647. Min Range: -0.1647

Max Act: 0.1056. Min Act: -0.0001

Data Index: 300146 (C4 (Web Text))

Max Activating Token Index: 380