Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2084 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.6181. Min Act: -0.0003

Data Index: 890378 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.6039. Min Act: -0.0003

Data Index: 1159281 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.6138. Min Act: -0.0003

Data Index: 1305927 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5994. Min Act: -0.0003

Data Index: 1327264 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5952. Min Act: -0.0003

Data Index: 178142 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5743. Min Act: -0.0003

Data Index: 808683 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5929. Min Act: -0.0003

Data Index: 581558 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5866. Min Act: -0.0003

Data Index: 706796 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5864. Min Act: -0.0003

Data Index: 121183 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5736. Min Act: -0.0003

Data Index: 554277 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5566. Min Act: -0.0003

Data Index: 232665 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5708. Min Act: -0.0003

Data Index: 924566 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5293. Min Act: -0.0003

Data Index: 491940 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5623. Min Act: -0.0003

Data Index: 642176 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5274. Min Act: -0.0003

Data Index: 606139 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5449. Min Act: -0.0003

Data Index: 1276101 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5227. Min Act: -0.0003

Data Index: 1277851 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5224. Min Act: -0.0003

Data Index: 1283122 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5223. Min Act: -0.0003

Data Index: 613256 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.6181. Min Range: -0.6181

Max Act: 0.5609. Min Act: -0.0003

Data Index: 1206473 (C4 (Web Text))

Max Activating Token Index: 561