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

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

Neuron 2107 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.2347. Min Act: -0.0001

Data Index: 1203214 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9940. Min Act: -0.0001

Data Index: 1165421 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9275. Min Act: -0.0001

Data Index: 661354 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9080. Min Act: -0.0001

Data Index: 13169 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.9054. Min Act: -0.0001

Data Index: 527718 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8757. Min Act: -0.0001

Data Index: 1294615 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8776. Min Act: -0.0001

Data Index: 992638 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8926. Min Act: -0.0001

Data Index: 1300889 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8415. Min Act: -0.0001

Data Index: 832680 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8527. Min Act: -0.0001

Data Index: 559930 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.8182. Min Act: -0.0001

Data Index: 316100 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7800. Min Act: -0.0001

Data Index: 798735 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7612. Min Act: -0.0001

Data Index: 457478 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7171. Min Act: -0.0001

Data Index: 908331 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7529. Min Act: -0.0001

Data Index: 1313588 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7526. Min Act: -0.0001

Data Index: 395241 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7483. Min Act: -0.0001

Data Index: 1352735 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7639. Min Act: -0.0001

Data Index: 1268180 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.6916. Min Act: -0.0001

Data Index: 239934 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 1.2347. Min Range: -1.2347

Max Act: 0.7302. Min Act: -0.0001

Data Index: 281004 (C4 (Web Text))

Max Activating Token Index: 144