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

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

Neuron 2090 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.7841. Min Act: -0.0001

Data Index: 845010 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6428. Min Act: -0.0002

Data Index: 748537 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.6138. Min Act: -0.0001

Data Index: 587022 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.4276. Min Act: -0.0001

Data Index: 295496 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.5569. Min Act: -0.0001

Data Index: 236650 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.5657. Min Act: -0.0001

Data Index: 806024 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.3245. Min Act: -0.0001

Data Index: 578470 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.2166. Min Act: -0.0002

Data Index: 1038470 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.3262. Min Act: -0.0002

Data Index: 608302 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.2329. Min Act: -0.0001

Data Index: 1271960 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.3618. Min Act: -0.0002

Data Index: 866999 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 3.7841. Min Range: -3.7841

Max Act: 2.8823. Min Act: -0.0002

Data Index: 496031 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.3068. Min Act: -0.0002

Data Index: 82541 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.4304. Min Act: -0.0001

Data Index: 222430 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.1340. Min Act: -0.0002

Data Index: 851586 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.1325. Min Act: -0.0002

Data Index: 518060 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 3.7841. Min Range: -3.7841

Max Act: 2.8597. Min Act: -0.0001

Data Index: 113289 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.0933. Min Act: -0.0002

Data Index: 90602 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 3.7841. Min Range: -3.7841

Max Act: 2.9080. Min Act: -0.0002

Data Index: 1090042 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 3.7841. Min Range: -3.7841

Max Act: 3.3379. Min Act: -0.0001

Data Index: 314273 (C4 (Web Text))

Max Activating Token Index: 863