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

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

Neuron 4146 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: 1.1622. Min Range: -1.1622

Max Act: 1.1326. Min Act: -0.0001

Data Index: 1226005 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 1.1622. Min Range: -1.1622

Max Act: 1.1622. Min Act: -0.0001

Data Index: 565278 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 1.1622. Min Range: -1.1622

Max Act: 1.0791. Min Act: -0.0001

Data Index: 735387 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9744. Min Act: -0.0001

Data Index: 1073031 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9992. Min Act: -0.0001

Data Index: 153587 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.1622. Min Range: -1.1622

Max Act: 1.0496. Min Act: -0.0001

Data Index: 15738 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9512. Min Act: -0.0001

Data Index: 301283 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9761. Min Act: -0.0001

Data Index: 490516 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9521. Min Act: -0.0001

Data Index: 1009441 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9398. Min Act: -0.0001

Data Index: 490745 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9272. Min Act: -0.0001

Data Index: 303096 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9280. Min Act: -0.0001

Data Index: 1217195 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.8896. Min Act: -0.0001

Data Index: 1271214 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9521. Min Act: -0.0001

Data Index: 187978 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9221. Min Act: -0.0001

Data Index: 1266825 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9263. Min Act: -0.0001

Data Index: 59816 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1008096 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9142. Min Act: -0.0001

Data Index: 311423 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9135. Min Act: -0.0001

Data Index: 679586 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 1.1622. Min Range: -1.1622

Max Act: 0.9658. Min Act: -0.0001

Data Index: 288046 (C4 (Web Text))

Max Activating Token Index: 33