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

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

Neuron 3580 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: 1.8032. Min Range: -1.8032

Max Act: 1.8032. Min Act: -0.0000

Data Index: 1099303 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.6150. Min Act: -0.0000

Data Index: 655648 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.6130. Min Act: -0.0000

Data Index: 1190960 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.4829. Min Act: -0.0000

Data Index: 139818 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.3779. Min Act: -0.0000

Data Index: 668511 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.4524. Min Act: -0.0000

Data Index: 879398 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.4776. Min Act: -0.0000

Data Index: 1262264 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.3979. Min Act: -0.0000

Data Index: 1166865 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.4830. Min Act: -0.0000

Data Index: 222539 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.3399. Min Act: -0.0000

Data Index: 732133 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.3208. Min Act: -0.0000

Data Index: 1265339 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.3188. Min Act: -0.0000

Data Index: 371407 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.1724. Min Act: -0.0000

Data Index: 902745 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.3329. Min Act: -0.0000

Data Index: 702056 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1093107 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.2612. Min Act: -0.0000

Data Index: 20365 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.2929. Min Act: -0.0000

Data Index: 1018761 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.2554. Min Act: -0.0000

Data Index: 1196168 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.2387. Min Act: -0.0000

Data Index: 457290 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 1.8032. Min Range: -1.8032

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1316901 (C4 (Web Text))

Max Activating Token Index: 971