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

Dataset: The Pile

Neuron 4981 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5254. Min Range: -1.5254

Max Act: 1.5254. Min Act: -0.0000

Data Index: 602651 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 1.5254. Min Range: -1.5254

Max Act: 1.2169. Min Act: -0.0000

Data Index: 154716 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.9883. Min Act: -0.0000

Data Index: 491466 (The Pile)

Max Activating Token Index: 444

Text #3

Max Range: 1.5254. Min Range: -1.5254

Max Act: 1.0100. Min Act: -0.0000

Data Index: 365826 (The Pile)

Max Activating Token Index: 67

Text #4

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1686545 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1304904 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.9147. Min Act: -0.0000

Data Index: 178890 (The Pile)

Max Activating Token Index: 99

Text #7

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.8371. Min Act: -0.0000

Data Index: 46624 (The Pile)

Max Activating Token Index: 805

Text #8

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.8672. Min Act: -0.0000

Data Index: 60343 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.9039. Min Act: 0.0000

Data Index: 1001829 (The Pile)

Max Activating Token Index: 219

Text #10

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.8883. Min Act: -0.0000

Data Index: 1405489 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1051492 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1165678 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1155562 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1078879 (The Pile)

Max Activating Token Index: 310

Text #15

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.7417. Min Act: -0.0000

Data Index: 797746 (The Pile)

Max Activating Token Index: 785

Text #16

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1756600 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1690463 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1353446 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 1.5254. Min Range: -1.5254

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1422485 (The Pile)

Max Activating Token Index: 715