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

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

Neuron 909 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: 2.8186. Min Range: -2.8186

Max Act: 2.8186. Min Act: -0.0000

Data Index: 960062 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.7151. Min Act: -0.0000

Data Index: 1283946 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.6029. Min Act: -0.0000

Data Index: 895785 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.4675. Min Act: -0.0000

Data Index: 867439 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.4460. Min Act: -0.0000

Data Index: 757387 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.4082. Min Act: -0.0000

Data Index: 771287 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.2041. Min Act: -0.0000

Data Index: 50684 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.4136. Min Act: -0.0000

Data Index: 1178353 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.2699. Min Act: -0.0000

Data Index: 611418 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.2462. Min Act: -0.0000

Data Index: 222701 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.2336. Min Act: -0.0000

Data Index: 1284417 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.3454. Min Act: -0.0000

Data Index: 1213634 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.1906. Min Act: -0.0000

Data Index: 172950 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.2316. Min Act: -0.0000

Data Index: 11948 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.1125. Min Act: -0.0000

Data Index: 656417 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.1158. Min Act: -0.0000

Data Index: 204446 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.1146. Min Act: -0.0000

Data Index: 1137630 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.0168. Min Act: -0.0000

Data Index: 672482 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 2.8186. Min Range: -2.8186

Max Act: 1.9690. Min Act: -0.0000

Data Index: 845224 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 2.8186. Min Range: -2.8186

Max Act: 2.0719. Min Act: -0.0000

Data Index: 1183156 (C4 (Web Text))

Max Activating Token Index: 1006