Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1690 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0228. Min Act: -0.0006

Data Index: 334412 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0201. Min Act: -0.0005

Data Index: 1552713 (Python Code)

Max Activating Token Index: 651

Text #2

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0192. Min Act: -0.0006

Data Index: 407842 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0191. Min Act: -0.0005

Data Index: 1433813 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0177. Min Act: -0.0005

Data Index: 764630 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0172. Min Act: -0.0005

Data Index: 1445955 (Python Code)

Max Activating Token Index: 795

Text #6

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0176. Min Act: -0.0005

Data Index: 1600989 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0170. Min Act: -0.0004

Data Index: 1406260 (Python Code)

Max Activating Token Index: 648

Text #8

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0169. Min Act: -0.0005

Data Index: 1469624 (Python Code)

Max Activating Token Index: 1019

Text #9

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0168. Min Act: -0.0005

Data Index: 980806 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0168. Min Act: -0.0005

Data Index: 1565662 (Python Code)

Max Activating Token Index: 270

Text #11

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0165. Min Act: -0.0005

Data Index: 1572318 (Python Code)

Max Activating Token Index: 421

Text #12

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0167. Min Act: -0.0005

Data Index: 1557745 (Python Code)

Max Activating Token Index: 818

Text #13

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0163. Min Act: -0.0005

Data Index: 1484140 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0166. Min Act: -0.0005

Data Index: 1189830 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0165. Min Act: -0.0005

Data Index: 54509 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0161. Min Act: -0.0005

Data Index: 1582341 (Python Code)

Max Activating Token Index: 768

Text #17

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0164. Min Act: -0.0005

Data Index: 922155 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0162. Min Act: -0.0005

Data Index: 1237536 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.0228. Min Range: -0.0228

Max Act: 0.0166. Min Act: -0.0005

Data Index: 1561937 (Python Code)

Max Activating Token Index: 543