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

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

Neuron 927 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: 0.1458. Min Range: -0.1458

Max Act: 0.1434. Min Act: -0.0001

Data Index: 395790 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1164003 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1458. Min Act: -0.0001

Data Index: 194315 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1356. Min Act: -0.0001

Data Index: 1262494 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1061169 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1090172 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1226. Min Act: -0.0001

Data Index: 607729 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1232. Min Act: -0.0001

Data Index: 475435 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1179. Min Act: -0.0001

Data Index: 273515 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1176. Min Act: -0.0001

Data Index: 604739 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1147. Min Act: -0.0001

Data Index: 851122 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1232. Min Act: -0.0001

Data Index: 930317 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1166. Min Act: -0.0001

Data Index: 3409 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.0999. Min Act: -0.0001

Data Index: 245809 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1132. Min Act: -0.0001

Data Index: 61766 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1309524 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1069. Min Act: -0.0001

Data Index: 633534 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1056. Min Act: -0.0001

Data Index: 89616 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1060. Min Act: -0.0001

Data Index: 960658 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.1458. Min Range: -0.1458

Max Act: 0.1066. Min Act: -0.0001

Data Index: 593026 (C4 (Web Text))

Max Activating Token Index: 1007