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

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

Neuron 4365 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1318491 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3825. Min Act: -0.0000

Data Index: 243318 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3537. Min Act: -0.0000

Data Index: 773664 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3360. Min Act: 0.0000

Data Index: 897308 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3308. Min Act: 0.0000

Data Index: 43507 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1197340 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2787. Min Act: -0.0000

Data Index: 37488 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3035. Min Act: -0.0000

Data Index: 379363 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3264. Min Act: 0.0000

Data Index: 418670 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2957. Min Act: -0.0000

Data Index: 268867 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.3063. Min Act: -0.0000

Data Index: 691026 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2708. Min Act: -0.0000

Data Index: 354558 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1091054 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2850. Min Act: -0.0000

Data Index: 586599 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2868. Min Act: -0.0000

Data Index: 43751 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2677. Min Act: -0.0000

Data Index: 1136507 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2604. Min Act: -0.0000

Data Index: 802422 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2852. Min Act: 0.0000

Data Index: 901440 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1262973 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.4174. Min Range: -0.4174

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1003526 (C4 (Web Text))

Max Activating Token Index: 192