Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 481 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0159. Min Act: -0.0006

Data Index: 500690 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0146. Min Act: -0.0006

Data Index: 278704 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0136. Min Act: -0.0006

Data Index: 277026 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0134. Min Act: -0.0006

Data Index: 672704 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1274311 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0132. Min Act: -0.0006

Data Index: 499930 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0139. Min Act: -0.0006

Data Index: 604931 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0135. Min Act: -0.0006

Data Index: 266815 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0129. Min Act: -0.0006

Data Index: 506906 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0127. Min Act: -0.0006

Data Index: 891820 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0147. Min Act: -0.0006

Data Index: 669908 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0126. Min Act: -0.0006

Data Index: 416744 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0129. Min Act: -0.0006

Data Index: 442776 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1199962 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0117. Min Act: -0.0006

Data Index: 611717 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0138. Min Act: -0.0006

Data Index: 770447 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1000456 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0128. Min Act: -0.0006

Data Index: 175565 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0138. Min Act: -0.0006

Data Index: 273262 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.0159. Min Range: -0.0159

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1109278 (C4 (Web Text))

Max Activating Token Index: 338