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

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

Neuron 2946 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: 1.5026. Min Range: -1.5026

Max Act: 1.5026. Min Act: -0.0001

Data Index: 158390 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.4826. Min Act: -0.0001

Data Index: 140740 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.3815. Min Act: -0.0001

Data Index: 911994 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.3244. Min Act: -0.0001

Data Index: 405687 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.4067. Min Act: -0.0001

Data Index: 586721 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.3542. Min Act: -0.0001

Data Index: 917923 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.3374. Min Act: -0.0001

Data Index: 684957 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.2549. Min Act: -0.0001

Data Index: 432016 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.1495. Min Act: -0.0001

Data Index: 324234 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.3238. Min Act: -0.0001

Data Index: 562494 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.1982. Min Act: -0.0001

Data Index: 186345 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.2246. Min Act: -0.0001

Data Index: 928658 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.2462. Min Act: -0.0001

Data Index: 1029980 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.2369. Min Act: -0.0001

Data Index: 3700 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.2542. Min Act: -0.0001

Data Index: 585784 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.2845. Min Act: -0.0001

Data Index: 1165772 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.2215. Min Act: -0.0001

Data Index: 331001 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.1827. Min Act: -0.0001

Data Index: 615790 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.1170. Min Act: -0.0001

Data Index: 1331022 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 1.5026. Min Range: -1.5026

Max Act: 1.1082. Min Act: -0.0001

Data Index: 1095907 (C4 (Web Text))

Max Activating Token Index: 1019