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

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

Neuron 5099 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: 3.5269. Min Range: -3.5269

Max Act: 3.5062. Min Act: -0.0001

Data Index: 413719 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.5269. Min Act: -0.0001

Data Index: 74768 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.3622. Min Act: -0.0001

Data Index: 365600 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.4133. Min Act: -0.0001

Data Index: 1184775 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.4155. Min Act: -0.0001

Data Index: 1341056 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.3982. Min Act: -0.0001

Data Index: 462568 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.2539. Min Act: -0.0001

Data Index: 1317726 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.3824. Min Act: -0.0001

Data Index: 677889 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.4001. Min Act: -0.0001

Data Index: 868113 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.2659. Min Act: -0.0001

Data Index: 1256627 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.3843. Min Act: -0.0001

Data Index: 394621 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.2799. Min Act: -0.0001

Data Index: 323457 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.3034. Min Act: -0.0001

Data Index: 1177392 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.1362. Min Act: -0.0001

Data Index: 920939 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.4104. Min Act: -0.0001

Data Index: 550913 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.2810. Min Act: -0.0001

Data Index: 238121 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 3.5269. Min Range: -3.5269

Max Act: 2.9908. Min Act: -0.0001

Data Index: 112332 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.1230. Min Act: -0.0001

Data Index: 400706 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.2758. Min Act: -0.0001

Data Index: 1193946 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 3.5269. Min Range: -3.5269

Max Act: 3.1348. Min Act: -0.0001

Data Index: 1280252 (C4 (Web Text))

Max Activating Token Index: 134