Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2549 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.3848. Min Range: -5.3848

Max Act: 5.3848. Min Act: -0.0001

Data Index: 1261572 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 5.3848. Min Range: -5.3848

Max Act: 4.5036. Min Act: -0.0001

Data Index: 536771 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 5.3848. Min Range: -5.3848

Max Act: 4.5723. Min Act: -0.0001

Data Index: 577972 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 5.3848. Min Range: -5.3848

Max Act: 4.2060. Min Act: -0.0001

Data Index: 1105901 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 5.3848. Min Range: -5.3848

Max Act: 4.6436. Min Act: -0.0001

Data Index: 1247557 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 5.3848. Min Range: -5.3848

Max Act: 4.0265. Min Act: -0.0001

Data Index: 1277170 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 5.3848. Min Range: -5.3848

Max Act: 3.9421. Min Act: -0.0001

Data Index: 1319095 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 5.3848. Min Range: -5.3848

Max Act: 3.8140. Min Act: -0.0001

Data Index: 77561 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 5.3848. Min Range: -5.3848

Max Act: 3.8196. Min Act: -0.0001

Data Index: 376308 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 5.3848. Min Range: -5.3848

Max Act: 4.1171. Min Act: -0.0001

Data Index: 341421 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 5.3848. Min Range: -5.3848

Max Act: 4.2233. Min Act: -0.0001

Data Index: 973133 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 5.3848. Min Range: -5.3848

Max Act: 4.0565. Min Act: -0.0001

Data Index: 847396 (C4 (Web Text))

Max Activating Token Index: 526

Text #12

Max Range: 5.3848. Min Range: -5.3848

Max Act: 4.5237. Min Act: -0.0001

Data Index: 331425 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 5.3848. Min Range: -5.3848

Max Act: 3.8086. Min Act: -0.0001

Data Index: 554219 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 5.3848. Min Range: -5.3848

Max Act: 3.8981. Min Act: -0.0001

Data Index: 405738 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 5.3848. Min Range: -5.3848

Max Act: 4.0847. Min Act: -0.0000

Data Index: 481166 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 5.3848. Min Range: -5.3848

Max Act: 3.7138. Min Act: -0.0001

Data Index: 786347 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 5.3848. Min Range: -5.3848

Max Act: 3.8212. Min Act: -0.0001

Data Index: 1243107 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 5.3848. Min Range: -5.3848

Max Act: 3.3186. Min Act: -0.0001

Data Index: 234613 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 5.3848. Min Range: -5.3848

Max Act: 3.4190. Min Act: -0.0001

Data Index: 897680 (C4 (Web Text))

Max Activating Token Index: 592