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

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

Neuron 1771 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2168. Min Range: -1.2168

Max Act: 1.2137. Min Act: -0.0001

Data Index: 804988 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 1.2168. Min Range: -1.2168

Max Act: 1.2168. Min Act: -0.0001

Data Index: 647451 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.2168. Min Range: -1.2168

Max Act: 1.1878. Min Act: -0.0001

Data Index: 925361 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 1.2168. Min Range: -1.2168

Max Act: 1.1275. Min Act: -0.0001

Data Index: 74218 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 1.2168. Min Range: -1.2168

Max Act: 1.0464. Min Act: -0.0001

Data Index: 197583 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 1.2168. Min Range: -1.2168

Max Act: 1.0374. Min Act: -0.0001

Data Index: 889270 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 1.2168. Min Range: -1.2168

Max Act: 1.0242. Min Act: -0.0001

Data Index: 1007113 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 1.2168. Min Range: -1.2168

Max Act: 1.0051. Min Act: -0.0001

Data Index: 211957 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 1.2168. Min Range: -1.2168

Max Act: 1.0022. Min Act: -0.0001

Data Index: 817674 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 1.2168. Min Range: -1.2168

Max Act: 0.9968. Min Act: -0.0001

Data Index: 1001490 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 1.2168. Min Range: -1.2168

Max Act: 0.9561. Min Act: -0.0001

Data Index: 837174 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 1.2168. Min Range: -1.2168

Max Act: 0.9185. Min Act: -0.0001

Data Index: 813843 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 1.2168. Min Range: -1.2168

Max Act: 0.8853. Min Act: -0.0001

Data Index: 572547 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.2168. Min Range: -1.2168

Max Act: 0.9000. Min Act: -0.0001

Data Index: 221803 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 1.2168. Min Range: -1.2168

Max Act: 0.9036. Min Act: -0.0001

Data Index: 233177 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.2168. Min Range: -1.2168

Max Act: 0.8925. Min Act: -0.0001

Data Index: 761372 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 1.2168. Min Range: -1.2168

Max Act: 0.9191. Min Act: -0.0001

Data Index: 1304502 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 1.2168. Min Range: -1.2168

Max Act: 0.9564. Min Act: -0.0001

Data Index: 471446 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 1.2168. Min Range: -1.2168

Max Act: 0.8542. Min Act: -0.0001

Data Index: 474999 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 1.2168. Min Range: -1.2168

Max Act: 0.9265. Min Act: -0.0001

Data Index: 316613 (C4 (Web Text))

Max Activating Token Index: 147