Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2914 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8763. Min Act: -0.0000

Data Index: 872878 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1295172 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8333. Min Act: -0.0000

Data Index: 418414 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8561. Min Act: -0.0000

Data Index: 537835 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8038. Min Act: -0.0000

Data Index: 740944 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8168. Min Act: -0.0000

Data Index: 796752 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.8227. Min Act: -0.0000

Data Index: 419745 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7787. Min Act: -0.0000

Data Index: 717868 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7450. Min Act: -0.0000

Data Index: 641038 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7490. Min Act: -0.0000

Data Index: 365385 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7156. Min Act: -0.0000

Data Index: 226215 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1037792 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6558. Min Act: -0.0000

Data Index: 649818 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6324. Min Act: -0.0000

Data Index: 43516 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6348. Min Act: -0.0000

Data Index: 701754 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6553. Min Act: -0.0000

Data Index: 833173 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1011525 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6246. Min Act: -0.0000

Data Index: 668945 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1310094 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.8763. Min Range: -0.8763

Max Act: 0.6293. Min Act: -0.0000

Data Index: 160087 (C4 (Web Text))

Max Activating Token Index: 651