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

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

Neuron 2290 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.6856. Min Act: -0.0000

Data Index: 1100343 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.6456. Min Act: -0.0000

Data Index: 208632 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.8146. Min Act: -0.0000

Data Index: 1222906 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.7172. Min Act: -0.0000

Data Index: 295111 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.6951. Min Act: -0.0000

Data Index: 1084283 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.7679. Min Act: -0.0000

Data Index: 255173 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.7525. Min Act: -0.0000

Data Index: 524361 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.7043. Min Act: -0.0000

Data Index: 940818 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.7129. Min Act: -0.0000

Data Index: 242257 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.6186. Min Act: -0.0000

Data Index: 941100 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.6708. Min Act: -0.0000

Data Index: 790874 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.5594. Min Act: -0.0001

Data Index: 1079113 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.4878. Min Act: -0.0000

Data Index: 924641 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.7274. Min Act: -0.0000

Data Index: 641479 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.7410. Min Act: -0.0000

Data Index: 78210 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.5365. Min Act: -0.0001

Data Index: 1194727 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.6074. Min Act: -0.0000

Data Index: 1238847 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.6113. Min Act: -0.0000

Data Index: 79839 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.4537. Min Act: -0.0000

Data Index: 565641 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 1.8146. Min Range: -1.8146

Max Act: 1.7057. Min Act: -0.0000

Data Index: 828355 (C4 (Web Text))

Max Activating Token Index: 825