Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2208 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.8142. Min Act: -0.0000

Data Index: 123403 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.7581. Min Act: -0.0000

Data Index: 694221 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.7126. Min Act: -0.0000

Data Index: 979299 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6763. Min Act: -0.0000

Data Index: 291472 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1171687 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1117053 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6909. Min Act: -0.0000

Data Index: 661376 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1163675 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6785. Min Act: -0.0000

Data Index: 472454 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1475867 (Python Code)

Max Activating Token Index: 614

Text #10

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6563. Min Act: -0.0000

Data Index: 281567 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6464. Min Act: -0.0000

Data Index: 93202 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1292544 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1295615 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6138. Min Act: -0.0000

Data Index: 948667 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1010658 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6015. Min Act: -0.0000

Data Index: 773475 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6202. Min Act: -0.0000

Data Index: 9141 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6564. Min Act: -0.0000

Data Index: 470185 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.8142. Min Range: -0.8142

Max Act: 0.6098. Min Act: -0.0000

Data Index: 584421 (C4 (Web Text))

Max Activating Token Index: 193