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

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

Neuron 2559 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: 5.2223. Min Range: -5.2223

Max Act: 5.1079. Min Act: -0.0000

Data Index: 1532634 (Python Code)

Max Activating Token Index: 359

Text #1

Max Range: 5.2223. Min Range: -5.2223

Max Act: 5.2223. Min Act: -0.0000

Data Index: 1638142 (Python Code)

Max Activating Token Index: 463

Text #2

Max Range: 5.2223. Min Range: -5.2223

Max Act: 4.6349. Min Act: -0.0000

Data Index: 1602165 (Python Code)

Max Activating Token Index: 420

Text #3

Max Range: 5.2223. Min Range: -5.2223

Max Act: 4.4519. Min Act: -0.0000

Data Index: 1400630 (Python Code)

Max Activating Token Index: 747

Text #4

Max Range: 5.2223. Min Range: -5.2223

Max Act: 4.3219. Min Act: -0.0000

Data Index: 1502406 (Python Code)

Max Activating Token Index: 338

Text #5

Max Range: 5.2223. Min Range: -5.2223

Max Act: 4.0977. Min Act: -0.0000

Data Index: 1488183 (Python Code)

Max Activating Token Index: 998

Text #6

Max Range: 5.2223. Min Range: -5.2223

Max Act: 4.0010. Min Act: -0.0000

Data Index: 1489591 (Python Code)

Max Activating Token Index: 713

Text #7

Max Range: 5.2223. Min Range: -5.2223

Max Act: 4.0612. Min Act: -0.0000

Data Index: 1591744 (Python Code)

Max Activating Token Index: 704

Text #8

Max Range: 5.2223. Min Range: -5.2223

Max Act: 4.0242. Min Act: -0.0000

Data Index: 1360681 (Python Code)

Max Activating Token Index: 485

Text #9

Max Range: 5.2223. Min Range: -5.2223

Max Act: 4.3583. Min Act: -0.0000

Data Index: 1472908 (Python Code)

Max Activating Token Index: 153

Text #10

Max Range: 5.2223. Min Range: -5.2223

Max Act: 4.1110. Min Act: -0.0000

Data Index: 1397114 (Python Code)

Max Activating Token Index: 364

Text #11

Max Range: 5.2223. Min Range: -5.2223

Max Act: 4.3170. Min Act: -0.0000

Data Index: 1370449 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 5.2223. Min Range: -5.2223

Max Act: 3.9545. Min Act: 0.0000

Data Index: 1480129 (Python Code)

Max Activating Token Index: 824

Text #13

Max Range: 5.2223. Min Range: -5.2223

Max Act: 3.9216. Min Act: -0.0000

Data Index: 1582377 (Python Code)

Max Activating Token Index: 814

Text #14

Max Range: 5.2223. Min Range: -5.2223

Max Act: 4.0424. Min Act: -0.0000

Data Index: 1481054 (Python Code)

Max Activating Token Index: 491

Text #15

Max Range: 5.2223. Min Range: -5.2223

Max Act: 3.9943. Min Act: -0.0000

Data Index: 1628556 (Python Code)

Max Activating Token Index: 782

Text #16

Max Range: 5.2223. Min Range: -5.2223

Max Act: 3.8970. Min Act: -0.0000

Data Index: 1392481 (Python Code)

Max Activating Token Index: 537

Text #17

Max Range: 5.2223. Min Range: -5.2223

Max Act: 3.8502. Min Act: -0.0000

Data Index: 1421961 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 5.2223. Min Range: -5.2223

Max Act: 3.6781. Min Act: -0.0000

Data Index: 1487580 (Python Code)

Max Activating Token Index: 209

Text #19

Max Range: 5.2223. Min Range: -5.2223

Max Act: 3.8521. Min Act: -0.0000

Data Index: 1423796 (Python Code)

Max Activating Token Index: 143