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

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

Neuron 1140 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1153. Min Range: -1.1153

Max Act: 1.0154. Min Act: -0.0001

Data Index: 750528 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 1.1153. Min Range: -1.1153

Max Act: 1.0674. Min Act: -0.0001

Data Index: 684197 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 1.1153. Min Range: -1.1153

Max Act: 1.1153. Min Act: -0.0001

Data Index: 139505 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 1.1153. Min Range: -1.1153

Max Act: 1.0093. Min Act: -0.0001

Data Index: 588611 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 1.1153. Min Range: -1.1153

Max Act: 1.0306. Min Act: -0.0001

Data Index: 938227 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9194. Min Act: -0.0001

Data Index: 1260417 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8907. Min Act: -0.0001

Data Index: 469220 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 1.1153. Min Range: -1.1153

Max Act: 1.0144. Min Act: -0.0001

Data Index: 655940 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9369. Min Act: -0.0001

Data Index: 720355 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9612. Min Act: -0.0001

Data Index: 1092769 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 1.1153. Min Range: -1.1153

Max Act: 1.0058. Min Act: -0.0001

Data Index: 1532808 (Python Code)

Max Activating Token Index: 440

Text #11

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9446. Min Act: -0.0001

Data Index: 972829 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9025. Min Act: -0.0001

Data Index: 335701 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9271. Min Act: -0.0001

Data Index: 197877 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9850. Min Act: -0.0001

Data Index: 1236314 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8962. Min Act: -0.0001

Data Index: 85219 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9340. Min Act: -0.0001

Data Index: 171572 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8548. Min Act: -0.0001

Data Index: 763662 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.8771. Min Act: -0.0001

Data Index: 843038 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 1.1153. Min Range: -1.1153

Max Act: 0.9744. Min Act: -0.0001

Data Index: 1344187 (C4 (Web Text))

Max Activating Token Index: 367