Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4362 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1132. Min Range: -2.1132

Max Act: 2.0594. Min Act: -0.0000

Data Index: 1013432 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 2.1132. Min Range: -2.1132

Max Act: 2.1132. Min Act: -0.0000

Data Index: 451405 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.8421. Min Act: -0.0000

Data Index: 807945 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.9502. Min Act: -0.0000

Data Index: 779033 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.7366. Min Act: -0.0000

Data Index: 32507 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.7898. Min Act: -0.0000

Data Index: 856209 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.6986. Min Act: -0.0000

Data Index: 417752 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.6155. Min Act: -0.0000

Data Index: 1281413 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.4530. Min Act: -0.0000

Data Index: 1227754 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.5388. Min Act: -0.0000

Data Index: 582348 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.5260. Min Act: -0.0000

Data Index: 759109 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.5152. Min Act: -0.0000

Data Index: 103165 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.4708. Min Act: -0.0000

Data Index: 163644 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.4726. Min Act: -0.0000

Data Index: 1145112 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.4584. Min Act: -0.0000

Data Index: 668811 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.4414. Min Act: -0.0000

Data Index: 92990 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.4292. Min Act: -0.0000

Data Index: 110001 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.4284. Min Act: -0.0000

Data Index: 233601 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.4237. Min Act: -0.0000

Data Index: 1277329 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 2.1132. Min Range: -2.1132

Max Act: 1.4095. Min Act: -0.0000

Data Index: 912554 (C4 (Web Text))

Max Activating Token Index: 437