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

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

Neuron 551 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.3207. Min Act: -0.0001

Data Index: 1204601 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2967. Min Act: -0.0000

Data Index: 70082 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2910. Min Act: -0.0001

Data Index: 925843 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2869. Min Act: -0.0000

Data Index: 214205 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2847. Min Act: -0.0001

Data Index: 1006463 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2606. Min Act: -0.0001

Data Index: 1252333 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2512. Min Act: -0.0001

Data Index: 883740 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2505. Min Act: -0.0001

Data Index: 308679 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2456. Min Act: -0.0001

Data Index: 968079 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2490. Min Act: -0.0001

Data Index: 398905 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2466. Min Act: -0.0000

Data Index: 783086 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2469. Min Act: -0.0000

Data Index: 146486 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2421. Min Act: -0.0001

Data Index: 1065437 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2356. Min Act: -0.0001

Data Index: 711549 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2429. Min Act: -0.0001

Data Index: 187713 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2396. Min Act: -0.0001

Data Index: 826423 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2284. Min Act: -0.0000

Data Index: 107822 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2550. Min Act: -0.0001

Data Index: 652766 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2155. Min Act: -0.0001

Data Index: 572817 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.3207. Min Range: -0.3207

Max Act: 0.2215. Min Act: -0.0001

Data Index: 1557706 (Python Code)

Max Activating Token Index: 790