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

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

Neuron 3842 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: 1.3119. Min Range: -1.3119

Max Act: 1.2810. Min Act: -0.0001

Data Index: 65761 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.3119. Min Act: -0.0002

Data Index: 588364 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.2710. Min Act: -0.0002

Data Index: 524847 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.3001. Min Act: -0.0001

Data Index: 500221 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.1874. Min Act: -0.0002

Data Index: 976818 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0939. Min Act: -0.0001

Data Index: 390684 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.1875. Min Act: -0.0002

Data Index: 247414 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.1226. Min Act: -0.0001

Data Index: 653108 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.1242. Min Act: -0.0002

Data Index: 1053133 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.2144. Min Act: -0.0002

Data Index: 1259208 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0733. Min Act: -0.0001

Data Index: 774020 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0968. Min Act: -0.0001

Data Index: 468581 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0930. Min Act: -0.0001

Data Index: 426596 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0784. Min Act: -0.0002

Data Index: 1334928 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 1.3119. Min Range: -1.3119

Max Act: 0.9895. Min Act: -0.0002

Data Index: 869266 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 1.3119. Min Range: -1.3119

Max Act: 0.9517. Min Act: -0.0001

Data Index: 956711 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 1.3119. Min Range: -1.3119

Max Act: 0.9422. Min Act: -0.0001

Data Index: 1140349 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0287. Min Act: -0.0001

Data Index: 112576 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 1.3119. Min Range: -1.3119

Max Act: 0.9635. Min Act: -0.0001

Data Index: 393921 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.3119. Min Range: -1.3119

Max Act: 1.0497. Min Act: -0.0002

Data Index: 858632 (C4 (Web Text))

Max Activating Token Index: 110