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

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

Neuron 3039 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.4630. Min Act: -0.0000

Data Index: 566445 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1027856 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1548332 (Python Code)

Max Activating Token Index: 114

Text #3

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.3074. Min Act: -0.0000

Data Index: 57668 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2872. Min Act: -0.0000

Data Index: 439178 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1410563 (Python Code)

Max Activating Token Index: 949

Text #6

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1397118 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1452121 (Python Code)

Max Activating Token Index: 186

Text #8

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1256210 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2657. Min Act: -0.0000

Data Index: 223428 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1471784 (Python Code)

Max Activating Token Index: 860

Text #11

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1639537 (Python Code)

Max Activating Token Index: 299

Text #12

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2192. Min Act: -0.0000

Data Index: 90123 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2378. Min Act: -0.0000

Data Index: 366114 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2504. Min Act: -0.0000

Data Index: 789123 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2339. Min Act: -0.0000

Data Index: 183825 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2317. Min Act: -0.0000

Data Index: 421336 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1360708 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2182. Min Act: -0.0000

Data Index: 1582887 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.4630. Min Range: -0.4630

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1562594 (Python Code)

Max Activating Token Index: 140