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

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

Neuron 14 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.8672. Min Act: -0.0001

Data Index: 764072 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.8769. Min Act: -0.0001

Data Index: 78644 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.7763. Min Act: -0.0001

Data Index: 123560 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.7501. Min Act: -0.0001

Data Index: 1213910 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.7022. Min Act: -0.0001

Data Index: 550772 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.6539. Min Act: -0.0001

Data Index: 582457 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.7183. Min Act: -0.0001

Data Index: 1240491 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.6620. Min Act: -0.0001

Data Index: 11359 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.7054. Min Act: -0.0001

Data Index: 1286427 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.7363. Min Act: -0.0001

Data Index: 86470 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.6396. Min Act: -0.0001

Data Index: 657350 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.6323. Min Act: -0.0001

Data Index: 897162 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.6198. Min Act: -0.0001

Data Index: 100075 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.6314. Min Act: -0.0001

Data Index: 491847 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.6228. Min Act: -0.0001

Data Index: 448944 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.6796. Min Act: -0.0001

Data Index: 1052019 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.5815. Min Act: -0.0001

Data Index: 917312 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.6542. Min Act: -0.0001

Data Index: 571059 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.5631. Min Act: -0.0001

Data Index: 92895 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 1.8769. Min Range: -1.8769

Max Act: 1.6012. Min Act: -0.0001

Data Index: 515353 (C4 (Web Text))

Max Activating Token Index: 42