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

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

Neuron 5893 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: 4.2203. Min Range: -4.2203

Max Act: 4.2203. Min Act: -0.0000

Data Index: 1345318 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 4.2203. Min Range: -4.2203

Max Act: 4.1737. Min Act: -0.0000

Data Index: 1151523 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 4.2203. Min Range: -4.2203

Max Act: 3.1904. Min Act: -0.0000

Data Index: 450413 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 4.2203. Min Range: -4.2203

Max Act: 3.3213. Min Act: -0.0000

Data Index: 428731 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 4.2203. Min Range: -4.2203

Max Act: 3.0963. Min Act: -0.0000

Data Index: 156223 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.8723. Min Act: -0.0000

Data Index: 1162324 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.7135. Min Act: -0.0000

Data Index: 813286 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.6689. Min Act: -0.0000

Data Index: 1195792 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.9157. Min Act: -0.0000

Data Index: 941887 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.7718. Min Act: -0.0000

Data Index: 759022 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.6218. Min Act: -0.0000

Data Index: 725512 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.5522. Min Act: -0.0000

Data Index: 12175 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.5221. Min Act: -0.0000

Data Index: 522673 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.3122. Min Act: -0.0000

Data Index: 321380 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.4418. Min Act: -0.0000

Data Index: 488364 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.4125. Min Act: -0.0000

Data Index: 332348 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.4127. Min Act: -0.0000

Data Index: 1355676 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.4128. Min Act: -0.0000

Data Index: 97379 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.4056. Min Act: -0.0000

Data Index: 1113738 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 4.2203. Min Range: -4.2203

Max Act: 2.5324. Min Act: -0.0000

Data Index: 1358289 (C4 (Web Text))

Max Activating Token Index: 820