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

Dataset: The Pile

Neuron 3199 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4482. Min Act: -0.0000

Data Index: 899135 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3478. Min Act: -0.0000

Data Index: 59054 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3423. Min Act: -0.0000

Data Index: 174462 (The Pile)

Max Activating Token Index: 892

Text #3

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3514. Min Act: -0.0000

Data Index: 892786 (The Pile)

Max Activating Token Index: 461

Text #4

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3600. Min Act: -0.0000

Data Index: 331035 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3451. Min Act: -0.0000

Data Index: 671189 (The Pile)

Max Activating Token Index: 942

Text #6

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3544. Min Act: -0.0000

Data Index: 612317 (The Pile)

Max Activating Token Index: 617

Text #7

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3234. Min Act: -0.0000

Data Index: 127194 (The Pile)

Max Activating Token Index: 125

Text #8

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3212. Min Act: -0.0000

Data Index: 178611 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3324. Min Act: -0.0000

Data Index: 93167 (The Pile)

Max Activating Token Index: 439

Text #10

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3351. Min Act: -0.0000

Data Index: 755043 (The Pile)

Max Activating Token Index: 724

Text #11

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3134. Min Act: -0.0000

Data Index: 1856664 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1793270 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1619961 (The Pile)

Max Activating Token Index: 565

Text #14

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1877030 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1184703 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1201677 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2852. Min Act: -0.0000

Data Index: 1254198 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1737045 (The Pile)

Max Activating Token Index: 164

Text #19

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.2871. Min Act: -0.0000

Data Index: 786943 (The Pile)

Max Activating Token Index: 1019