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

Dataset: The Pile

Neuron 2854 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: 3.8938. Min Range: -3.8938

Max Act: 3.8938. Min Act: -0.0000

Data Index: 958745 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 3.8938. Min Range: -3.8938

Max Act: 2.6024. Min Act: -0.0000

Data Index: 919847 (The Pile)

Max Activating Token Index: 275

Text #2

Max Range: 3.8938. Min Range: -3.8938

Max Act: 2.5401. Min Act: -0.0000

Data Index: 1855488 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 3.8938. Min Range: -3.8938

Max Act: 2.4880. Min Act: -0.0000

Data Index: 412090 (The Pile)

Max Activating Token Index: 954

Text #4

Max Range: 3.8938. Min Range: -3.8938

Max Act: 2.1111. Min Act: -0.0000

Data Index: 241512 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 3.8938. Min Range: -3.8938

Max Act: 2.2628. Min Act: -0.0000

Data Index: 1377056 (The Pile)

Max Activating Token Index: 470

Text #6

Max Range: 3.8938. Min Range: -3.8938

Max Act: 2.0699. Min Act: -0.0000

Data Index: 116115 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 3.8938. Min Range: -3.8938

Max Act: 2.2152. Min Act: -0.0000

Data Index: 633402 (The Pile)

Max Activating Token Index: 356

Text #8

Max Range: 3.8938. Min Range: -3.8938

Max Act: 2.0453. Min Act: -0.0000

Data Index: 1540540 (The Pile)

Max Activating Token Index: 689

Text #9

Max Range: 3.8938. Min Range: -3.8938

Max Act: 1.9949. Min Act: -0.0000

Data Index: 802471 (The Pile)

Max Activating Token Index: 763

Text #10

Max Range: 3.8938. Min Range: -3.8938

Max Act: 2.1247. Min Act: -0.0000

Data Index: 878903 (The Pile)

Max Activating Token Index: 975

Text #11

Max Range: 3.8938. Min Range: -3.8938

Max Act: 1.7208. Min Act: -0.0000

Data Index: 1902107 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 3.8938. Min Range: -3.8938

Max Act: 1.7997. Min Act: -0.0000

Data Index: 1748575 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 3.8938. Min Range: -3.8938

Max Act: 1.8235. Min Act: -0.0000

Data Index: 1971061 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 3.8938. Min Range: -3.8938

Max Act: 1.8358. Min Act: -0.0000

Data Index: 1308376 (The Pile)

Max Activating Token Index: 391

Text #15

Max Range: 3.8938. Min Range: -3.8938

Max Act: 1.6073. Min Act: -0.0000

Data Index: 1374892 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 3.8938. Min Range: -3.8938

Max Act: 1.6578. Min Act: -0.0000

Data Index: 381074 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 3.8938. Min Range: -3.8938

Max Act: 1.6368. Min Act: -0.0000

Data Index: 278286 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 3.8938. Min Range: -3.8938

Max Act: 1.8309. Min Act: -0.0000

Data Index: 516421 (The Pile)

Max Activating Token Index: 680

Text #19

Max Range: 3.8938. Min Range: -3.8938

Max Act: 1.4958. Min Act: -0.0000

Data Index: 1670052 (The Pile)

Max Activating Token Index: 892