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

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

Neuron 2527 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1032813 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0256. Min Act: -0.0004

Data Index: 787091 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0250. Min Act: -0.0004

Data Index: 60925 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0236. Min Act: -0.0004

Data Index: 178148 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1298307 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0221. Min Act: -0.0003

Data Index: 721886 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0220. Min Act: -0.0004

Data Index: 310792 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0221. Min Act: -0.0004

Data Index: 372138 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0221. Min Act: -0.0003

Data Index: 216623 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0221. Min Act: -0.0004

Data Index: 344656 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1085570 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0213. Min Act: -0.0003

Data Index: 436394 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0214. Min Act: -0.0003

Data Index: 1231365 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1276593 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0217. Min Act: -0.0003

Data Index: 460046 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0217. Min Act: -0.0003

Data Index: 1350512 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0217. Min Act: -0.0004

Data Index: 1230245 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0216. Min Act: -0.0003

Data Index: 706518 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0215. Min Act: -0.0003

Data Index: 686141 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0261. Min Range: -0.0261

Max Act: 0.0214. Min Act: -0.0004

Data Index: 824384 (C4 (Web Text))

Max Activating Token Index: 833