Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 268 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3736. Min Range: -1.3736

Max Act: 1.3736. Min Act: -0.0001

Data Index: 1164819 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.3736. Min Range: -1.3736

Max Act: 1.0942. Min Act: -0.0001

Data Index: 1219215 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.3736. Min Range: -1.3736

Max Act: 1.0292. Min Act: -0.0001

Data Index: 187110 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.8293. Min Act: -0.0001

Data Index: 465078 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.9179. Min Act: -0.0001

Data Index: 1184064 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.8340. Min Act: -0.0001

Data Index: 743158 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.9417. Min Act: -0.0001

Data Index: 1067072 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.9043. Min Act: -0.0001

Data Index: 1282986 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.7891. Min Act: -0.0001

Data Index: 1309163 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.7891. Min Act: -0.0001

Data Index: 826598 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.8477. Min Act: -0.0001

Data Index: 1273134 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.7469. Min Act: -0.0001

Data Index: 199333 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.7718. Min Act: -0.0000

Data Index: 609712 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.7651. Min Act: -0.0001

Data Index: 420114 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.6985. Min Act: -0.0001

Data Index: 837839 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.7078. Min Act: -0.0001

Data Index: 1168138 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.7092. Min Act: -0.0001

Data Index: 475551 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.6990. Min Act: -0.0001

Data Index: 1306112 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.7865. Min Act: -0.0001

Data Index: 408793 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 1.3736. Min Range: -1.3736

Max Act: 0.6653. Min Act: -0.0001

Data Index: 958164 (C4 (Web Text))

Max Activating Token Index: 201