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

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

Neuron 148 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.8287. Min Act: -0.0001

Data Index: 1246459 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.7541. Min Act: -0.0001

Data Index: 327415 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4741. Min Act: -0.0001

Data Index: 752447 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.6049. Min Act: -0.0001

Data Index: 1157212 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5031. Min Act: -0.0001

Data Index: 186368 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.5188. Min Act: -0.0001

Data Index: 760934 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4280. Min Act: -0.0001

Data Index: 957335 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4081. Min Act: -0.0001

Data Index: 279240 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.3570. Min Act: -0.0001

Data Index: 528222 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.4601. Min Act: -0.0001

Data Index: 1002527 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.3043. Min Act: -0.0001

Data Index: 894949 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.3109. Min Act: -0.0001

Data Index: 101170 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.3040. Min Act: -0.0001

Data Index: 1233010 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.2222. Min Act: -0.0001

Data Index: 1313881 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.2876. Min Act: -0.0001

Data Index: 754584 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.3560. Min Act: -0.0001

Data Index: 1189127 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.2764. Min Act: -0.0001

Data Index: 814506 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.2283. Min Act: -0.0001

Data Index: 1199732 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.3428. Min Act: -0.0001

Data Index: 65740 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 1.8287. Min Range: -1.8287

Max Act: 1.3746. Min Act: -0.0001

Data Index: 130743 (C4 (Web Text))

Max Activating Token Index: 902