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

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

Neuron 1077 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1268. Min Range: -1.1268

Max Act: 1.1268. Min Act: -0.0001

Data Index: 1151227 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 1.1268. Min Range: -1.1268

Max Act: 1.0703. Min Act: -0.0001

Data Index: 978418 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9765. Min Act: -0.0001

Data Index: 1246217 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9957. Min Act: -0.0001

Data Index: 330706 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8981. Min Act: -0.0001

Data Index: 207942 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8821. Min Act: -0.0001

Data Index: 725503 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9807. Min Act: -0.0001

Data Index: 129598 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8746. Min Act: -0.0001

Data Index: 286286 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9003. Min Act: -0.0001

Data Index: 1294786 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8630. Min Act: -0.0001

Data Index: 1310092 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8388. Min Act: -0.0001

Data Index: 771056 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8406. Min Act: -0.0001

Data Index: 404032 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7316. Min Act: -0.0001

Data Index: 311312 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8152. Min Act: -0.0001

Data Index: 785009 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8169. Min Act: -0.0001

Data Index: 698253 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7975. Min Act: -0.0001

Data Index: 1317268 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.6831. Min Act: -0.0001

Data Index: 1166583 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7089. Min Act: -0.0001

Data Index: 947010 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7000. Min Act: -0.0001

Data Index: 271558 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7372. Min Act: -0.0001

Data Index: 595742 (C4 (Web Text))

Max Activating Token Index: 508