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

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

Neuron 2358 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: 1.1284. Min Range: -1.1284

Max Act: 1.1284. Min Act: -0.0001

Data Index: 308280 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 1.1284. Min Range: -1.1284

Max Act: 1.0394. Min Act: -0.0001

Data Index: 429463 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 1.1284. Min Range: -1.1284

Max Act: 1.0319. Min Act: -0.0001

Data Index: 1220547 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9534. Min Act: -0.0001

Data Index: 752672 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9644. Min Act: -0.0001

Data Index: 1047747 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9450. Min Act: -0.0001

Data Index: 411877 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9186. Min Act: -0.0001

Data Index: 1027191 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9699. Min Act: -0.0001

Data Index: 242816 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9432. Min Act: -0.0001

Data Index: 1294733 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9259. Min Act: -0.0001

Data Index: 116259 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9321. Min Act: -0.0001

Data Index: 229155 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9923. Min Act: -0.0001

Data Index: 455992 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.8831. Min Act: -0.0001

Data Index: 851270 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9287. Min Act: -0.0001

Data Index: 674830 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.8052. Min Act: -0.0001

Data Index: 110017 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9125. Min Act: -0.0001

Data Index: 888664 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9655. Min Act: -0.0001

Data Index: 194341 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9508. Min Act: -0.0001

Data Index: 392785 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9162. Min Act: -0.0001

Data Index: 940884 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 1.1284. Min Range: -1.1284

Max Act: 0.9738. Min Act: -0.0001

Data Index: 333556 (C4 (Web Text))

Max Activating Token Index: 200