Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2978 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.2094. Min Act: -0.0000

Data Index: 925945 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.1062. Min Act: -0.0000

Data Index: 309003 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1125900 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.0555. Min Act: -0.0000

Data Index: 390643 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.0282. Min Act: -0.0000

Data Index: 120025 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9158. Min Act: -0.0000

Data Index: 646514 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1195742 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9467. Min Act: -0.0000

Data Index: 439309 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9116. Min Act: -0.0000

Data Index: 180107 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1014083 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8735. Min Act: -0.0000

Data Index: 927446 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1253001 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1328727 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8525. Min Act: -0.0000

Data Index: 397521 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8404. Min Act: -0.0000

Data Index: 215251 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8066. Min Act: -0.0000

Data Index: 566818 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8252. Min Act: -0.0000

Data Index: 224627 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8156. Min Act: -0.0000

Data Index: 847512 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8606. Min Act: -0.0000

Data Index: 1071484 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8339. Min Act: -0.0000

Data Index: 772193 (C4 (Web Text))

Max Activating Token Index: 555