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

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

Neuron 5714 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.3274. Min Act: -0.0000

Data Index: 360357 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1308. Min Act: -0.0000

Data Index: 1165666 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1851. Min Act: -0.0000

Data Index: 146020 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.2693. Min Act: -0.0000

Data Index: 474707 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1424. Min Act: -0.0000

Data Index: 502419 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1685. Min Act: -0.0000

Data Index: 436291 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.0490. Min Act: -0.0000

Data Index: 85468 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.9572. Min Act: -0.0000

Data Index: 756294 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1227341 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.0894. Min Act: -0.0000

Data Index: 1622114 (Python Code)

Max Activating Token Index: 928

Text #10

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.0305. Min Act: -0.0000

Data Index: 416715 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.1076. Min Act: -0.0000

Data Index: 227390 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1276658 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.0008. Min Act: -0.0000

Data Index: 408350 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.0235. Min Act: -0.0000

Data Index: 84844 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 1.3274. Min Range: -1.3274

Max Act: 1.0259. Min Act: -0.0000

Data Index: 200704 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.9620. Min Act: -0.0000

Data Index: 703624 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.8287. Min Act: -0.0000

Data Index: 386156 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.9749. Min Act: -0.0000

Data Index: 332077 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 1.3274. Min Range: -1.3274

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1087743 (C4 (Web Text))

Max Activating Token Index: 461