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

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

Neuron 3734 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0137. Min Act: -0.0003

Data Index: 182072 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0136. Min Act: -0.0003

Data Index: 1283025 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0131. Min Act: -0.0004

Data Index: 721344 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1239721 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0120. Min Act: -0.0003

Data Index: 644716 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1180585 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0123. Min Act: -0.0003

Data Index: 850924 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0120. Min Act: -0.0003

Data Index: 51740 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1301999 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1387549 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0116. Min Act: -0.0003

Data Index: 383825 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0119. Min Act: -0.0003

Data Index: 827109 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1255580 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1656356 (Python Code)

Max Activating Token Index: 692

Text #14

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0118. Min Act: -0.0003

Data Index: 734164 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0114. Min Act: -0.0003

Data Index: 924089 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1352022 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0112. Min Act: -0.0003

Data Index: 459334 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0109. Min Act: -0.0003

Data Index: 953740 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0137. Min Range: -0.0137

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1221604 (C4 (Web Text))

Max Activating Token Index: 748