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

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

Neuron 269 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1431. Min Act: -0.0002

Data Index: 781098 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1438. Min Act: -0.0002

Data Index: 713494 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1436. Min Act: -0.0001

Data Index: 603409 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1236. Min Act: -0.0002

Data Index: 977021 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1268. Min Act: -0.0001

Data Index: 815245 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1233. Min Act: -0.0002

Data Index: 1319780 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1211. Min Act: -0.0002

Data Index: 1237748 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1176. Min Act: -0.0001

Data Index: 313280 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1159. Min Act: -0.0002

Data Index: 1018514 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1151. Min Act: -0.0001

Data Index: 571799 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1118. Min Act: -0.0002

Data Index: 7092 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1023. Min Act: -0.0002

Data Index: 895330 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1071. Min Act: -0.0001

Data Index: 288705 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0971. Min Act: -0.0002

Data Index: 201870 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0980. Min Act: -0.0001

Data Index: 94212 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1035481 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1024567 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1048673 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1012. Min Act: -0.0002

Data Index: 674138 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.1438. Min Range: -0.1438

Max Act: 0.1001. Min Act: -0.0001

Data Index: 261748 (C4 (Web Text))

Max Activating Token Index: 87