Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1241 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.6461. Min Act: -0.0000

Data Index: 59748 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.4872. Min Act: -0.0000

Data Index: 1047907 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.4716. Min Act: -0.0000

Data Index: 737332 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.4655. Min Act: -0.0000

Data Index: 497388 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.4128. Min Act: -0.0000

Data Index: 639675 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.3319. Min Act: -0.0000

Data Index: 446199 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.3141. Min Act: -0.0000

Data Index: 1035931 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.1396. Min Act: -0.0000

Data Index: 981970 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.2033. Min Act: -0.0000

Data Index: 1325556 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.2729. Min Act: -0.0000

Data Index: 366940 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.3229. Min Act: -0.0000

Data Index: 318549 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.2443. Min Act: -0.0000

Data Index: 1227493 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.3034. Min Act: -0.0000

Data Index: 280539 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.1285. Min Act: -0.0000

Data Index: 1147050 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.1053. Min Act: -0.0000

Data Index: 891627 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.1885. Min Act: -0.0000

Data Index: 551467 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.0440. Min Act: -0.0000

Data Index: 314181 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.0978. Min Act: -0.0000

Data Index: 998662 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.0988. Min Act: -0.0000

Data Index: 598946 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.6461. Min Range: -1.6461

Max Act: 1.1547. Min Act: -0.0000

Data Index: 542536 (C4 (Web Text))

Max Activating Token Index: 875