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

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

Neuron 3037 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.2092. Min Act: -0.0001

Data Index: 501747 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.2080. Min Act: -0.0001

Data Index: 798485 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.1407. Min Act: -0.0001

Data Index: 1398048 (Python Code)

Max Activating Token Index: 932

Text #3

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.1182. Min Act: -0.0001

Data Index: 504588 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.1181. Min Act: -0.0001

Data Index: 702248 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0824. Min Act: -0.0001

Data Index: 1084646 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0174. Min Act: -0.0001

Data Index: 1620342 (Python Code)

Max Activating Token Index: 360

Text #7

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.1213. Min Act: -0.0001

Data Index: 893935 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0448. Min Act: -0.0001

Data Index: 375114 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0071. Min Act: -0.0001

Data Index: 225829 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.1296. Min Act: -0.0001

Data Index: 1179415 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0260. Min Act: -0.0001

Data Index: 386002 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9721. Min Act: -0.0001

Data Index: 384322 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9663. Min Act: -0.0001

Data Index: 1042656 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9692. Min Act: -0.0001

Data Index: 1130105 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9943. Min Act: -0.0001

Data Index: 956815 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9436. Min Act: -0.0001

Data Index: 619753 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 1.2092. Min Range: -1.2092

Max Act: 1.0339. Min Act: -0.0001

Data Index: 1468599 (Python Code)

Max Activating Token Index: 316

Text #18

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9967. Min Act: -0.0001

Data Index: 385944 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 1.2092. Min Range: -1.2092

Max Act: 0.9112. Min Act: -0.0001

Data Index: 107326 (C4 (Web Text))

Max Activating Token Index: 1008