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

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

Neuron 4086 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: 2.8058. Min Range: -2.8058

Max Act: 2.8058. Min Act: -0.0000

Data Index: 613324 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.6397. Min Act: -0.0000

Data Index: 67283 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.6157. Min Act: -0.0000

Data Index: 763820 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.5647. Min Act: -0.0000

Data Index: 1034619 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.4087. Min Act: -0.0000

Data Index: 532874 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.4091. Min Act: -0.0000

Data Index: 552016 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.3420. Min Act: -0.0000

Data Index: 103406 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.3244. Min Act: -0.0000

Data Index: 1228903 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.3870. Min Act: -0.0000

Data Index: 638016 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.2516. Min Act: -0.0000

Data Index: 958679 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.1911. Min Act: -0.0000

Data Index: 1128632 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.2385. Min Act: -0.0000

Data Index: 813034 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.1263. Min Act: -0.0000

Data Index: 167378 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.0983. Min Act: -0.0000

Data Index: 162493 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 2.8058. Min Range: -2.8058

Max Act: 2.1150. Min Act: -0.0000

Data Index: 436398 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 2.8058. Min Range: -2.8058

Max Act: 1.9336. Min Act: -0.0000

Data Index: 343743 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 2.8058. Min Range: -2.8058

Max Act: 1.9284. Min Act: -0.0000

Data Index: 11604 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 2.8058. Min Range: -2.8058

Max Act: 1.9249. Min Act: -0.0000

Data Index: 537783 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 2.8058. Min Range: -2.8058

Max Act: 1.8119. Min Act: -0.0000

Data Index: 563963 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 2.8058. Min Range: -2.8058

Max Act: 1.7846. Min Act: -0.0000

Data Index: 894821 (C4 (Web Text))

Max Activating Token Index: 552