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

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

Neuron 3292 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.6496. Min Act: -0.0001

Data Index: 685793 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.6886. Min Act: -0.0001

Data Index: 1151356 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.6605. Min Act: -0.0001

Data Index: 643214 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.5478. Min Act: -0.0001

Data Index: 947146 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.4304. Min Act: -0.0001

Data Index: 158791 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.5147. Min Act: -0.0001

Data Index: 126436 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.4561. Min Act: -0.0001

Data Index: 864127 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.4434. Min Act: -0.0001

Data Index: 1130395 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.3865. Min Act: -0.0001

Data Index: 38925 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.4147. Min Act: -0.0001

Data Index: 498414 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.2831. Min Act: -0.0001

Data Index: 412662 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.4119. Min Act: -0.0001

Data Index: 849671 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.3805. Min Act: -0.0001

Data Index: 608509 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.2736. Min Act: -0.0001

Data Index: 52357 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.3572. Min Act: -0.0001

Data Index: 268113 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.3167. Min Act: -0.0001

Data Index: 313552 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.2454. Min Act: -0.0001

Data Index: 327068 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.2610. Min Act: -0.0001

Data Index: 417559 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.2283. Min Act: -0.0001

Data Index: 1156095 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 1.6886. Min Range: -1.6886

Max Act: 1.2132. Min Act: -0.0001

Data Index: 1117087 (C4 (Web Text))

Max Activating Token Index: 358