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

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

Neuron 4089 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.7884. Min Act: -0.0001

Data Index: 937496 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.3372. Min Act: -0.0001

Data Index: 480367 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0854. Min Act: -0.0001

Data Index: 1150119 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0974. Min Act: -0.0001

Data Index: 515889 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.2365. Min Act: -0.0001

Data Index: 864177 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0685. Min Act: -0.0001

Data Index: 427928 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.1888. Min Act: -0.0001

Data Index: 863551 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.9451. Min Act: -0.0001

Data Index: 523672 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.1024. Min Act: -0.0001

Data Index: 432035 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0921. Min Act: -0.0001

Data Index: 1334676 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.9564. Min Act: -0.0001

Data Index: 171406 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.1029. Min Act: -0.0001

Data Index: 1203431 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.9540. Min Act: -0.0001

Data Index: 474819 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0934. Min Act: -0.0001

Data Index: 1281881 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 3.7884. Min Range: -3.7884

Max Act: 3.0844. Min Act: -0.0001

Data Index: 963995 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.8190. Min Act: -0.0001

Data Index: 1040716 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.8115. Min Act: -0.0001

Data Index: 1164247 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.7948. Min Act: -0.0001

Data Index: 847434 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.8672. Min Act: -0.0001

Data Index: 641665 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 3.7884. Min Range: -3.7884

Max Act: 2.7715. Min Act: -0.0001

Data Index: 536165 (C4 (Web Text))

Max Activating Token Index: 32