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

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

Neuron 2657 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1406. Min Act: -0.0003

Data Index: 1171912 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1456. Min Act: -0.0003

Data Index: 802212 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1381. Min Act: -0.0003

Data Index: 447268 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1428. Min Act: -0.0003

Data Index: 168286 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1305. Min Act: -0.0003

Data Index: 70220 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1323. Min Act: -0.0003

Data Index: 1004542 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1308. Min Act: -0.0003

Data Index: 217265 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1212. Min Act: -0.0003

Data Index: 988047 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1039. Min Act: -0.0003

Data Index: 718284 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1198. Min Act: -0.0003

Data Index: 235928 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1344. Min Act: -0.0003

Data Index: 800701 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1207. Min Act: -0.0003

Data Index: 1163796 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1235. Min Act: -0.0003

Data Index: 315358 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1182. Min Act: -0.0003

Data Index: 1084086 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1133. Min Act: -0.0003

Data Index: 1349416 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1120. Min Act: -0.0003

Data Index: 1112012 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1166. Min Act: -0.0003

Data Index: 860045 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1151. Min Act: -0.0003

Data Index: 1052514 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1119. Min Act: -0.0003

Data Index: 316992 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.1456. Min Range: -0.1456

Max Act: 0.1098. Min Act: -0.0003

Data Index: 887000 (C4 (Web Text))

Max Activating Token Index: 935