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

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

Neuron 432 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: 1.2823. Min Range: -1.2823

Max Act: 1.2823. Min Act: -0.0001

Data Index: 1144008 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0984. Min Act: -0.0001

Data Index: 848629 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0317. Min Act: -0.0001

Data Index: 1047269 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.9265. Min Act: -0.0001

Data Index: 517212 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.9081. Min Act: -0.0001

Data Index: 106156 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.9608. Min Act: -0.0001

Data Index: 730406 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 1.2823. Min Range: -1.2823

Max Act: 1.0005. Min Act: -0.0001

Data Index: 244253 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.8641. Min Act: -0.0001

Data Index: 903259 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.9143. Min Act: -0.0001

Data Index: 1151404 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.8373. Min Act: -0.0001

Data Index: 335129 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.8398. Min Act: -0.0001

Data Index: 1326032 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.8820. Min Act: -0.0001

Data Index: 1121970 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.8337. Min Act: -0.0001

Data Index: 1296035 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.8025. Min Act: -0.0001

Data Index: 879868 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.8157. Min Act: -0.0001

Data Index: 576396 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.8390. Min Act: -0.0001

Data Index: 1005338 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.8215. Min Act: -0.0001

Data Index: 822616 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.7972. Min Act: -0.0001

Data Index: 1331576 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.7885. Min Act: -0.0001

Data Index: 1160138 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.2823. Min Range: -1.2823

Max Act: 0.8029. Min Act: -0.0001

Data Index: 680699 (C4 (Web Text))

Max Activating Token Index: 169