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

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

Neuron 4548 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1950. Min Act: 0.0000

Data Index: 562313 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1922. Min Act: 0.0000

Data Index: 598076 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1789. Min Act: -0.0000

Data Index: 587512 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1215035 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1753. Min Act: 0.0001

Data Index: 61551 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1555. Min Act: -0.0000

Data Index: 667022 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1367. Min Act: -0.0000

Data Index: 643174 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1119516 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1417. Min Act: -0.0000

Data Index: 405824 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1424. Min Act: 0.0000

Data Index: 566258 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1351. Min Act: -0.0000

Data Index: 305682 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1402. Min Act: -0.0000

Data Index: 479361 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1212. Min Act: -0.0000

Data Index: 133305 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1351. Min Act: -0.0000

Data Index: 192120 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1302. Min Act: -0.0000

Data Index: 563115 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1276. Min Act: -0.0000

Data Index: 856067 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1234. Min Act: -0.0000

Data Index: 477242 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1223. Min Act: -0.0000

Data Index: 365206 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1304. Min Act: 0.0000

Data Index: 768427 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1298324 (C4 (Web Text))

Max Activating Token Index: 208