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

Dataset: The Pile

Neuron 3624 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: 1.9278. Min Range: -1.9278

Max Act: 1.9278. Min Act: -0.0000

Data Index: 954116 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.5025. Min Act: -0.0000

Data Index: 86667 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.4174. Min Act: -0.0000

Data Index: 485133 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.4258. Min Act: -0.0000

Data Index: 1850864 (The Pile)

Max Activating Token Index: 298

Text #4

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.4826. Min Act: -0.0000

Data Index: 385665 (The Pile)

Max Activating Token Index: 866

Text #5

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.3927. Min Act: -0.0000

Data Index: 1269516 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.4529. Min Act: -0.0000

Data Index: 383211 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1656472 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.4034. Min Act: -0.0000

Data Index: 607950 (The Pile)

Max Activating Token Index: 927

Text #9

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.3298. Min Act: -0.0000

Data Index: 1053187 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.3934. Min Act: -0.0000

Data Index: 127675 (The Pile)

Max Activating Token Index: 261

Text #11

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.2425. Min Act: -0.0000

Data Index: 499844 (The Pile)

Max Activating Token Index: 591

Text #12

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.2198. Min Act: -0.0000

Data Index: 1574166 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.2958. Min Act: -0.0000

Data Index: 716430 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.2673. Min Act: -0.0000

Data Index: 288186 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.1872. Min Act: -0.0000

Data Index: 506345 (The Pile)

Max Activating Token Index: 668

Text #16

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.1791. Min Act: -0.0000

Data Index: 1669986 (The Pile)

Max Activating Token Index: 907

Text #17

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.2382. Min Act: -0.0000

Data Index: 752339 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.1569. Min Act: -0.0000

Data Index: 375668 (The Pile)

Max Activating Token Index: 922

Text #19

Max Range: 1.9278. Min Range: -1.9278

Max Act: 1.2343. Min Act: -0.0000

Data Index: 416014 (The Pile)

Max Activating Token Index: 996