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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 902 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1321439 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1144565 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0131. Min Act: -0.0003

Data Index: 646938 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0131. Min Act: -0.0003

Data Index: 158564 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0131. Min Act: -0.0003

Data Index: 886282 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0130. Min Act: -0.0003

Data Index: 283743 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0130. Min Act: -0.0003

Data Index: 490227 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0129. Min Act: -0.0003

Data Index: 490740 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0124. Min Act: -0.0003

Data Index: 337023 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1083171 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0126. Min Act: -0.0003

Data Index: 835292 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0003

Data Index: 221298 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0126. Min Act: -0.0003

Data Index: 223142 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0126. Min Act: -0.0003

Data Index: 582042 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1122087 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0125. Min Act: -0.0003

Data Index: 770265 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0124. Min Act: -0.0003

Data Index: 836953 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0003

Data Index: 77485 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0003

Data Index: 313969 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0003

Data Index: 665069 (C4 (Web Text))

Max Activating Token Index: 517