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

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

Neuron 3770 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7924. Min Range: -4.7924

Max Act: 4.7924. Min Act: -0.0000

Data Index: 613550 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 4.7924. Min Range: -4.7924

Max Act: 4.6147. Min Act: -0.0001

Data Index: 582306 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 4.7924. Min Range: -4.7924

Max Act: 4.4364. Min Act: -0.0001

Data Index: 450191 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 4.7924. Min Range: -4.7924

Max Act: 4.3879. Min Act: -0.0001

Data Index: 816052 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 4.7924. Min Range: -4.7924

Max Act: 4.2127. Min Act: -0.0001

Data Index: 801692 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 4.7924. Min Range: -4.7924

Max Act: 4.2562. Min Act: -0.0001

Data Index: 218127 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 4.7924. Min Range: -4.7924

Max Act: 4.2314. Min Act: -0.0000

Data Index: 867962 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 4.7924. Min Range: -4.7924

Max Act: 4.1302. Min Act: -0.0001

Data Index: 622117 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 4.7924. Min Range: -4.7924

Max Act: 4.1865. Min Act: -0.0000

Data Index: 1207312 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 4.7924. Min Range: -4.7924

Max Act: 3.9188. Min Act: -0.0001

Data Index: 1115133 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 4.7924. Min Range: -4.7924

Max Act: 3.7704. Min Act: -0.0000

Data Index: 445221 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 4.7924. Min Range: -4.7924

Max Act: 3.8252. Min Act: -0.0000

Data Index: 945959 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 4.7924. Min Range: -4.7924

Max Act: 3.9748. Min Act: -0.0001

Data Index: 1321409 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 4.7924. Min Range: -4.7924

Max Act: 3.8122. Min Act: -0.0001

Data Index: 1242371 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 4.7924. Min Range: -4.7924

Max Act: 3.9580. Min Act: -0.0001

Data Index: 1261848 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 4.7924. Min Range: -4.7924

Max Act: 3.9350. Min Act: -0.0001

Data Index: 1272594 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 4.7924. Min Range: -4.7924

Max Act: 3.7583. Min Act: -0.0001

Data Index: 1114418 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 4.7924. Min Range: -4.7924

Max Act: 3.9134. Min Act: -0.0000

Data Index: 1310606 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 4.7924. Min Range: -4.7924

Max Act: 3.9169. Min Act: -0.0001

Data Index: 944430 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 4.7924. Min Range: -4.7924

Max Act: 3.7226. Min Act: -0.0001

Data Index: 339518 (C4 (Web Text))

Max Activating Token Index: 162