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

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

Neuron 3979 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3163. Min Range: -1.3163

Max Act: 1.3163. Min Act: -0.0000

Data Index: 638206 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 1.3163. Min Range: -1.3163

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1281939 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.3163. Min Range: -1.3163

Max Act: 1.0768. Min Act: -0.0000

Data Index: 441303 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.3163. Min Range: -1.3163

Max Act: 1.0768. Min Act: -0.0000

Data Index: 774222 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 1.3163. Min Range: -1.3163

Max Act: 1.0592. Min Act: -0.0000

Data Index: 142215 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.3163. Min Range: -1.3163

Max Act: 1.0708. Min Act: -0.0000

Data Index: 302546 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.9691. Min Act: -0.0000

Data Index: 828186 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.9728. Min Act: -0.0000

Data Index: 1184800 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.9837. Min Act: -0.0000

Data Index: 1207169 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 1.3163. Min Range: -1.3163

Max Act: 1.0160. Min Act: -0.0000

Data Index: 520454 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.9503. Min Act: -0.0000

Data Index: 229410 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.9182. Min Act: -0.0000

Data Index: 665447 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.9331. Min Act: -0.0000

Data Index: 165165 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.9466. Min Act: -0.0000

Data Index: 73201 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.9010. Min Act: -0.0000

Data Index: 395384 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1183709 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1282423 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1164973 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.8555. Min Act: -0.0000

Data Index: 84371 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 1.3163. Min Range: -1.3163

Max Act: 0.8932. Min Act: -0.0000

Data Index: 639 (C4 (Web Text))

Max Activating Token Index: 262