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

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

Neuron 2264 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.5243. Min Act: -0.0002

Data Index: 356741 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.6199. Min Act: -0.0002

Data Index: 1358449 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.5086. Min Act: -0.0002

Data Index: 961189 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.4226. Min Act: -0.0002

Data Index: 1334970 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.4030. Min Act: -0.0002

Data Index: 625511 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.4048. Min Act: -0.0002

Data Index: 127555 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.4059. Min Act: -0.0002

Data Index: 541032 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.3759. Min Act: -0.0002

Data Index: 291035 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.3835. Min Act: -0.0002

Data Index: 1277200 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.3969. Min Act: -0.0002

Data Index: 19896 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.3018. Min Act: -0.0002

Data Index: 315751 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.5109. Min Act: -0.0002

Data Index: 1352878 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.2350. Min Act: -0.0002

Data Index: 764951 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.4710. Min Act: -0.0002

Data Index: 929716 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.5524. Min Act: -0.0002

Data Index: 594160 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.4982. Min Act: -0.0002

Data Index: 412599 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.3423. Min Act: -0.0002

Data Index: 794017 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.3169. Min Act: -0.0002

Data Index: 1154848 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.3126. Min Act: -0.0002

Data Index: 311038 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 1.6199. Min Range: -1.6199

Max Act: 1.2491. Min Act: -0.0002

Data Index: 573947 (C4 (Web Text))

Max Activating Token Index: 184