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

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

Neuron 2346 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.2924. Min Act: -0.0001

Data Index: 40007 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.3092. Min Act: -0.0001

Data Index: 805283 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1994. Min Act: -0.0001

Data Index: 114626 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1911. Min Act: -0.0001

Data Index: 517060 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1997. Min Act: -0.0001

Data Index: 448369 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.2066. Min Act: -0.0001

Data Index: 929756 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1638. Min Act: -0.0001

Data Index: 440251 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1682. Min Act: -0.0001

Data Index: 219455 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1101. Min Act: -0.0001

Data Index: 707414 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1374. Min Act: -0.0001

Data Index: 885348 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1401. Min Act: -0.0001

Data Index: 196906 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1482. Min Act: -0.0001

Data Index: 257149 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1379. Min Act: -0.0001

Data Index: 735076 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1362. Min Act: -0.0001

Data Index: 496073 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1961. Min Act: -0.0001

Data Index: 556092 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1256. Min Act: -0.0001

Data Index: 1082214 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1189. Min Act: -0.0001

Data Index: 735574 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.0569. Min Act: -0.0001

Data Index: 519356 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1120. Min Act: -0.0001

Data Index: 421295 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 1.3092. Min Range: -1.3092

Max Act: 1.1352. Min Act: -0.0001

Data Index: 57614 (C4 (Web Text))

Max Activating Token Index: 940