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

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

Neuron 5906 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: 0.1941. Min Range: -0.1941

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1283497 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1572. Min Act: -0.0000

Data Index: 905638 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1663. Min Act: -0.0000

Data Index: 879754 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1522. Min Act: -0.0000

Data Index: 132198 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1290. Min Act: -0.0000

Data Index: 5722 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1349093 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1461. Min Act: -0.0000

Data Index: 281791 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1464. Min Act: -0.0000

Data Index: 658845 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1391. Min Act: -0.0000

Data Index: 958093 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1349. Min Act: -0.0000

Data Index: 740628 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1275. Min Act: -0.0000

Data Index: 49968 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1339332 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1158. Min Act: -0.0000

Data Index: 853224 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1190. Min Act: -0.0000

Data Index: 225982 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1253. Min Act: -0.0000

Data Index: 804118 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1177. Min Act: -0.0000

Data Index: 128529 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1233. Min Act: -0.0000

Data Index: 557010 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1191. Min Act: -0.0000

Data Index: 692950 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1376. Min Act: -0.0000

Data Index: 785096 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.1941. Min Range: -0.1941

Max Act: 0.1096. Min Act: -0.0000

Data Index: 842997 (C4 (Web Text))

Max Activating Token Index: 341