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

Dataset: The Pile

Neuron 2520 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: 1.4816. Min Range: -1.4816

Max Act: 1.4816. Min Act: -0.0000

Data Index: 48195 (The Pile)

Max Activating Token Index: 199

Text #1

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.4524. Min Act: -0.0000

Data Index: 1377772 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1371529 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1910445 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.3670. Min Act: -0.0000

Data Index: 1313879 (The Pile)

Max Activating Token Index: 659

Text #5

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.1973. Min Act: -0.0000

Data Index: 746316 (The Pile)

Max Activating Token Index: 863

Text #6

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.3175. Min Act: -0.0000

Data Index: 219001 (The Pile)

Max Activating Token Index: 23

Text #7

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.2313. Min Act: -0.0000

Data Index: 1282454 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.1699. Min Act: -0.0000

Data Index: 920181 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.2371. Min Act: -0.0000

Data Index: 833867 (The Pile)

Max Activating Token Index: 435

Text #10

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1479900 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.1752. Min Act: -0.0000

Data Index: 1210869 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.1665. Min Act: -0.0000

Data Index: 265084 (The Pile)

Max Activating Token Index: 600

Text #13

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.1059. Min Act: -0.0000

Data Index: 935035 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.2195. Min Act: -0.0000

Data Index: 930354 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.2233. Min Act: -0.0000

Data Index: 1844138 (The Pile)

Max Activating Token Index: 528

Text #16

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.1352. Min Act: -0.0000

Data Index: 423250 (The Pile)

Max Activating Token Index: 497

Text #17

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.1048. Min Act: -0.0000

Data Index: 1233707 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.0967. Min Act: -0.0000

Data Index: 1075036 (The Pile)

Max Activating Token Index: 137

Text #19

Max Range: 1.4816. Min Range: -1.4816

Max Act: 1.0348. Min Act: -0.0000

Data Index: 336498 (The Pile)

Max Activating Token Index: 295