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

Dataset: The Pile

Neuron 4205 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4854. Min Act: -0.0000

Data Index: 476367 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1340476 (The Pile)

Max Activating Token Index: 684

Text #2

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1192093 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4253. Min Act: -0.0000

Data Index: 580609 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1050347 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1779862 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3523. Min Act: -0.0000

Data Index: 424681 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3418. Min Act: -0.0000

Data Index: 950472 (The Pile)

Max Activating Token Index: 844

Text #8

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3428. Min Act: -0.0000

Data Index: 527948 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1774275 (The Pile)

Max Activating Token Index: 487

Text #10

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1410063 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1076872 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2955. Min Act: -0.0000

Data Index: 296660 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1879221 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2943. Min Act: -0.0000

Data Index: 1703424 (The Pile)

Max Activating Token Index: 848

Text #15

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1188083 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3223. Min Act: -0.0000

Data Index: 918885 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1819885 (The Pile)

Max Activating Token Index: 858

Text #18

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3522. Min Act: -0.0000

Data Index: 1902967 (The Pile)

Max Activating Token Index: 412

Text #19

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1899132 (The Pile)

Max Activating Token Index: 306