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

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

Neuron 3758 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1293. Min Range: -2.1293

Max Act: 2.1293. Min Act: -0.0000

Data Index: 1222144 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.7369. Min Act: -0.0000

Data Index: 373216 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.6018. Min Act: -0.0000

Data Index: 301641 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.4744. Min Act: -0.0000

Data Index: 127036 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.3588. Min Act: -0.0000

Data Index: 527711 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.3250. Min Act: -0.0000

Data Index: 62118 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.3548. Min Act: -0.0000

Data Index: 954036 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1059096 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.2303. Min Act: -0.0000

Data Index: 44260 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1015850 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.2704. Min Act: -0.0000

Data Index: 214716 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.2581. Min Act: -0.0000

Data Index: 964666 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.2459. Min Act: -0.0000

Data Index: 586684 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1305522 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.0979. Min Act: -0.0000

Data Index: 476180 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.1493. Min Act: -0.0000

Data Index: 1079684 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.1313. Min Act: -0.0000

Data Index: 1113442 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.1049. Min Act: -0.0000

Data Index: 98048 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.1124. Min Act: -0.0000

Data Index: 376012 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 2.1293. Min Range: -2.1293

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1129193 (C4 (Web Text))

Max Activating Token Index: 288