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

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

Neuron 358 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.5166. Min Act: -0.0001

Data Index: 845458 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.2717. Min Act: -0.0001

Data Index: 1123602 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.0995. Min Act: -0.0001

Data Index: 262296 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.0676. Min Act: -0.0001

Data Index: 833622 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.2462. Min Act: -0.0001

Data Index: 227034 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.0592. Min Act: -0.0001

Data Index: 819713 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.0150. Min Act: -0.0001

Data Index: 605770 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.0507. Min Act: -0.0001

Data Index: 18789 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.0662. Min Act: -0.0001

Data Index: 85297 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.5166. Min Range: -1.5166

Max Act: 0.9704. Min Act: -0.0001

Data Index: 776847 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.0323. Min Act: -0.0001

Data Index: 817224 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 1.5166. Min Range: -1.5166

Max Act: 1.0228. Min Act: -0.0001

Data Index: 717287 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 1.5166. Min Range: -1.5166

Max Act: 0.9450. Min Act: -0.0001

Data Index: 1114093 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 1.5166. Min Range: -1.5166

Max Act: 0.8839. Min Act: -0.0001

Data Index: 834977 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.5166. Min Range: -1.5166

Max Act: 0.9416. Min Act: -0.0001

Data Index: 667288 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 1.5166. Min Range: -1.5166

Max Act: 0.9265. Min Act: -0.0001

Data Index: 116214 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 1.5166. Min Range: -1.5166

Max Act: 0.8917. Min Act: -0.0001

Data Index: 707251 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 1.5166. Min Range: -1.5166

Max Act: 0.9171. Min Act: -0.0001

Data Index: 924360 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 1.5166. Min Range: -1.5166

Max Act: 0.9424. Min Act: -0.0001

Data Index: 863682 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 1.5166. Min Range: -1.5166

Max Act: 0.9328. Min Act: -0.0001

Data Index: 1268675 (C4 (Web Text))

Max Activating Token Index: 22