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

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

Neuron 1128 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.9241. Min Act: -0.0000

Data Index: 642063 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1187838 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.8259. Min Act: -0.0000

Data Index: 749053 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.7384. Min Act: -0.0000

Data Index: 306583 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.5439. Min Act: -0.0000

Data Index: 726021 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.6825. Min Act: -0.0000

Data Index: 555949 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1321574 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.6449. Min Act: -0.0000

Data Index: 766313 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.6106. Min Act: -0.0000

Data Index: 495221 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.6056. Min Act: -0.0000

Data Index: 818826 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.5928. Min Act: -0.0000

Data Index: 653139 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.6286. Min Act: -0.0000

Data Index: 12542 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.6056. Min Act: -0.0000

Data Index: 60073 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.6254. Min Act: -0.0000

Data Index: 225667 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.5927. Min Act: -0.0000

Data Index: 659896 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1093032 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1078971 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.5931. Min Act: -0.0000

Data Index: 442206 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.4833. Min Act: -0.0000

Data Index: 878124 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.9241. Min Range: -0.9241

Max Act: 0.5441. Min Act: 0.0000

Data Index: 1187431 (C4 (Web Text))

Max Activating Token Index: 537