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

Dataset: The Pile

Neuron 1242 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.8524. Min Act: -0.0000

Data Index: 1814361 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.0187. Min Act: -0.0000

Data Index: 646993 (The Pile)

Max Activating Token Index: 790

Text #2

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.0593. Min Act: -0.0000

Data Index: 1548778 (The Pile)

Max Activating Token Index: 437

Text #3

Max Range: 3.8524. Min Range: -3.8524

Max Act: 3.1835. Min Act: -0.0000

Data Index: 429364 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.7139. Min Act: -0.0000

Data Index: 1185166 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.7234. Min Act: -0.0000

Data Index: 585146 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.8443. Min Act: -0.0000

Data Index: 632256 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.9115. Min Act: -0.0000

Data Index: 1220271 (The Pile)

Max Activating Token Index: 39

Text #8

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.8944. Min Act: -0.0000

Data Index: 323735 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.7017. Min Act: -0.0000

Data Index: 916565 (The Pile)

Max Activating Token Index: 586

Text #10

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.6664. Min Act: -0.0000

Data Index: 350865 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.3766. Min Act: -0.0000

Data Index: 358491 (The Pile)

Max Activating Token Index: 233

Text #12

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.5006. Min Act: -0.0000

Data Index: 1660979 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.6217. Min Act: -0.0000

Data Index: 960481 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.6074. Min Act: -0.0000

Data Index: 157263 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.6081. Min Act: -0.0000

Data Index: 453018 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.7272. Min Act: -0.0000

Data Index: 1387347 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.4457. Min Act: -0.0000

Data Index: 250085 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.5522. Min Act: -0.0000

Data Index: 839625 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 3.8524. Min Range: -3.8524

Max Act: 2.3716. Min Act: -0.0000

Data Index: 738063 (The Pile)

Max Activating Token Index: 328