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

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

Neuron 2874 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.2784. Min Act: -0.0001

Data Index: 897157 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.2872. Min Act: -0.0001

Data Index: 1011821 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.9769. Min Act: -0.0001

Data Index: 1074914 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1628. Min Act: -0.0001

Data Index: 17882 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.8958. Min Act: -0.0001

Data Index: 665503 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.8499. Min Act: -0.0001

Data Index: 819406 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.2679. Min Act: -0.0001

Data Index: 1195186 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.9520. Min Act: -0.0001

Data Index: 799945 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.0636. Min Act: -0.0001

Data Index: 1024422 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.8509. Min Act: -0.0001

Data Index: 1156822 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.7345. Min Act: -0.0001

Data Index: 635138 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.7185. Min Act: -0.0001

Data Index: 77098 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 3.2872. Min Range: -3.2872

Max Act: 3.1503. Min Act: -0.0001

Data Index: 706410 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.5201. Min Act: -0.0001

Data Index: 743729 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.8274. Min Act: -0.0001

Data Index: 1315759 (C4 (Web Text))

Max Activating Token Index: 947

Text #15

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.6453. Min Act: -0.0001

Data Index: 789525 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.7973. Min Act: -0.0001

Data Index: 1218611 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.3727. Min Act: -0.0001

Data Index: 256706 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.1980. Min Act: -0.0001

Data Index: 589883 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 3.2872. Min Range: -3.2872

Max Act: 2.8238. Min Act: -0.0001

Data Index: 1277213 (C4 (Web Text))

Max Activating Token Index: 772