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

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

Neuron 5106 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.9529. Min Act: -0.0000

Data Index: 1618028 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.7316. Min Act: -0.0000

Data Index: 1411495 (Python Code)

Max Activating Token Index: 433

Text #2

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.7276. Min Act: -0.0000

Data Index: 1459212 (Python Code)

Max Activating Token Index: 283

Text #3

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.5958. Min Act: -0.0000

Data Index: 1433705 (Python Code)

Max Activating Token Index: 553

Text #4

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.9151. Min Act: -0.0000

Data Index: 1468364 (Python Code)

Max Activating Token Index: 810

Text #5

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.3763. Min Act: -0.0000

Data Index: 1009113 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1525729 (Python Code)

Max Activating Token Index: 707

Text #7

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.4772. Min Act: -0.0000

Data Index: 1560546 (Python Code)

Max Activating Token Index: 369

Text #8

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.1285. Min Act: -0.0000

Data Index: 38959 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.1826. Min Act: -0.0000

Data Index: 1285316 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1147176 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.0189. Min Act: -0.0000

Data Index: 321216 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.0967. Min Act: -0.0000

Data Index: 1637018 (Python Code)

Max Activating Token Index: 513

Text #13

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.0965. Min Act: -0.0000

Data Index: 817957 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 1.9529. Min Range: -1.9529

Max Act: 0.9442. Min Act: -0.0000

Data Index: 87266 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1294697 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.0349. Min Act: -0.0000

Data Index: 32448 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 1.9529. Min Range: -1.9529

Max Act: 1.0338. Min Act: -0.0000

Data Index: 381432 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 1.9529. Min Range: -1.9529

Max Act: 0.9806. Min Act: -0.0000

Data Index: 553628 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 1.9529. Min Range: -1.9529

Max Act: 0.9715. Min Act: -0.0000

Data Index: 357488 (C4 (Web Text))

Max Activating Token Index: 382