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

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

Neuron 4802 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1419960 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2927. Min Act: -0.0000

Data Index: 716618 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2610. Min Act: -0.0000

Data Index: 218884 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1264755 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1070188 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1542594 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1463217 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2478. Min Act: -0.0000

Data Index: 1070410 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1512574 (Python Code)

Max Activating Token Index: 118

Text #9

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1194028 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2480. Min Act: -0.0000

Data Index: 1487784 (Python Code)

Max Activating Token Index: 254

Text #11

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1489850 (Python Code)

Max Activating Token Index: 206

Text #12

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2412. Min Act: -0.0000

Data Index: 49297 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1553064 (Python Code)

Max Activating Token Index: 43

Text #14

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2357. Min Act: -0.0000

Data Index: 572179 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2330. Min Act: -0.0000

Data Index: 1495104 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1223493 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1458858 (Python Code)

Max Activating Token Index: 785

Text #18

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1640351 (Python Code)

Max Activating Token Index: 117

Text #19

Max Range: 0.2945. Min Range: -0.2945

Max Act: 0.2186. Min Act: -0.0001

Data Index: 1415944 (Python Code)

Max Activating Token Index: 322