Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2702 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3618. Min Act: -0.0003

Data Index: 900187 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3424. Min Act: -0.0003

Data Index: 170315 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3470. Min Act: -0.0003

Data Index: 410230 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2837. Min Act: -0.0003

Data Index: 1092523 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3348. Min Act: -0.0003

Data Index: 200911 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3120. Min Act: -0.0003

Data Index: 1349569 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3306. Min Act: -0.0003

Data Index: 912830 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3063. Min Act: -0.0003

Data Index: 231124 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3068. Min Act: -0.0003

Data Index: 881207 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3176. Min Act: -0.0003

Data Index: 413852 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3131. Min Act: -0.0003

Data Index: 232663 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3110. Min Act: -0.0003

Data Index: 70430 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3014. Min Act: -0.0003

Data Index: 340922 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3220. Min Act: -0.0003

Data Index: 275393 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3007. Min Act: -0.0003

Data Index: 1319825 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2969. Min Act: -0.0003

Data Index: 269548 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3191. Min Act: -0.0003

Data Index: 414846 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2933. Min Act: -0.0003

Data Index: 253272 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.2952. Min Act: -0.0003

Data Index: 1073673 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.3618. Min Range: -0.3618

Max Act: 0.3072. Min Act: -0.0003

Data Index: 1240503 (C4 (Web Text))

Max Activating Token Index: 58