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

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

Neuron 5037 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7818. Min Act: -0.0001

Data Index: 672138 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7434. Min Act: -0.0001

Data Index: 1248331 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1229332 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1168523 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7210. Min Act: -0.0001

Data Index: 87515 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6481. Min Act: -0.0001

Data Index: 91049 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7058. Min Act: -0.0000

Data Index: 137812 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6180. Min Act: -0.0000

Data Index: 310536 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.7233. Min Act: -0.0001

Data Index: 66777 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6117. Min Act: -0.0001

Data Index: 310447 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6171. Min Act: -0.0001

Data Index: 692078 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6981. Min Act: -0.0000

Data Index: 665698 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6299. Min Act: -0.0000

Data Index: 711361 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1061307 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5647. Min Act: -0.0000

Data Index: 554249 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6135. Min Act: -0.0001

Data Index: 1036362 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6455. Min Act: -0.0001

Data Index: 827743 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5920. Min Act: -0.0000

Data Index: 107427 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1161992 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.7818. Min Range: -0.7818

Max Act: 0.6028. Min Act: -0.0001

Data Index: 305422 (C4 (Web Text))

Max Activating Token Index: 734