Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3281 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1872. Min Act: -0.0002

Data Index: 904830 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1636. Min Act: -0.0001

Data Index: 832517 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1666. Min Act: -0.0001

Data Index: 669716 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1587. Min Act: -0.0002

Data Index: 734864 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1335. Min Act: -0.0001

Data Index: 665504 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1270. Min Act: -0.0002

Data Index: 893189 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1305. Min Act: -0.0001

Data Index: 959029 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1212. Min Act: -0.0002

Data Index: 794723 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1302. Min Act: -0.0002

Data Index: 342150 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1276. Min Act: -0.0002

Data Index: 115971 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1307. Min Act: -0.0002

Data Index: 545387 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1265517 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1331862 (C4 (Web Text))

Max Activating Token Index: 917

Text #13

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1014049 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1101. Min Act: -0.0001

Data Index: 525013 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1107. Min Act: -0.0001

Data Index: 648839 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1158. Min Act: -0.0002

Data Index: 581204 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1123. Min Act: -0.0002

Data Index: 1054742 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1234. Min Act: -0.0002

Data Index: 1170977 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.1872. Min Range: -0.1872

Max Act: 0.1103. Min Act: -0.0002

Data Index: 923904 (C4 (Web Text))

Max Activating Token Index: 491