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

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

Neuron 3912 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.3169. Min Act: -0.0001

Data Index: 1150412 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.2707. Min Act: -0.0001

Data Index: 203018 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.1177. Min Act: -0.0001

Data Index: 157586 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0825. Min Act: -0.0001

Data Index: 622876 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9987. Min Act: -0.0001

Data Index: 465367 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.1083. Min Act: -0.0001

Data Index: 1320231 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.1223. Min Act: -0.0001

Data Index: 306575 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9209. Min Act: -0.0001

Data Index: 408149 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0361. Min Act: -0.0001

Data Index: 790532 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.1504. Min Act: -0.0001

Data Index: 619273 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0365. Min Act: -0.0001

Data Index: 788239 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9507. Min Act: -0.0001

Data Index: 154858 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.8937. Min Act: -0.0001

Data Index: 369191 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9805. Min Act: -0.0001

Data Index: 607557 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0433. Min Act: -0.0001

Data Index: 1291227 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9729. Min Act: -0.0001

Data Index: 1248162 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9411. Min Act: -0.0001

Data Index: 1271176 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9430. Min Act: -0.0001

Data Index: 904851 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0592. Min Act: -0.0001

Data Index: 137876 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9585. Min Act: -0.0001

Data Index: 665390 (C4 (Web Text))

Max Activating Token Index: 482