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

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

Neuron 1604 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.3265. Min Act: -0.0001

Data Index: 1026796 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.3039. Min Act: -0.0000

Data Index: 791730 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.2370. Min Act: -0.0001

Data Index: 1139375 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.1114. Min Act: -0.0001

Data Index: 208993 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.1001. Min Act: -0.0001

Data Index: 1078668 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.0207. Min Act: -0.0001

Data Index: 401594 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.3265. Min Range: -1.3265

Max Act: 0.9630. Min Act: -0.0001

Data Index: 253074 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.0866. Min Act: -0.0001

Data Index: 584265 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.0135. Min Act: -0.0001

Data Index: 1319419 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 1.3265. Min Range: -1.3265

Max Act: 0.9855. Min Act: -0.0001

Data Index: 414419 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.1195. Min Act: -0.0000

Data Index: 8694 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1073533 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.0693. Min Act: -0.0000

Data Index: 158525 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.0271. Min Act: -0.0001

Data Index: 1316074 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 1.3265. Min Range: -1.3265

Max Act: 1.0470. Min Act: -0.0001

Data Index: 413050 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 1.3265. Min Range: -1.3265

Max Act: 0.9273. Min Act: -0.0001

Data Index: 1148635 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 1.3265. Min Range: -1.3265

Max Act: 0.9664. Min Act: -0.0001

Data Index: 1126402 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 1.3265. Min Range: -1.3265

Max Act: 0.9641. Min Act: -0.0001

Data Index: 478810 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 1.3265. Min Range: -1.3265

Max Act: 0.9889. Min Act: -0.0000

Data Index: 594388 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.3265. Min Range: -1.3265

Max Act: 0.9927. Min Act: -0.0001

Data Index: 26039 (C4 (Web Text))

Max Activating Token Index: 934