Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 197 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.4401. Min Act: -0.0000

Data Index: 802205 (The Pile)

Max Activating Token Index: 936

Text #1

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1162644 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1949075 (The Pile)

Max Activating Token Index: 286

Text #3

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2227. Min Act: -0.0000

Data Index: 46169 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2284. Min Act: -0.0000

Data Index: 235136 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2378. Min Act: -0.0000

Data Index: 341139 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2238. Min Act: -0.0000

Data Index: 709858 (The Pile)

Max Activating Token Index: 831

Text #7

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1168027 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2124. Min Act: -0.0000

Data Index: 343412 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2256. Min Act: -0.0000

Data Index: 287146 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1257500 (The Pile)

Max Activating Token Index: 872

Text #11

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.1956. Min Act: -0.0000

Data Index: 1540569 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1195932 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1683906 (The Pile)

Max Activating Token Index: 466

Text #14

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1716328 (The Pile)

Max Activating Token Index: 799

Text #15

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1491265 (The Pile)

Max Activating Token Index: 844

Text #16

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.1817. Min Act: -0.0000

Data Index: 763535 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1328842 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1045694 (The Pile)

Max Activating Token Index: 757

Text #19

Max Range: 0.4401. Min Range: -0.4401

Max Act: 0.1922. Min Act: -0.0000

Data Index: 204687 (The Pile)

Max Activating Token Index: 112