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

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

Neuron 2999 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: 3.3132. Min Range: -3.3132

Max Act: 3.2103. Min Act: -0.0001

Data Index: 105356 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 3.3132. Min Range: -3.3132

Max Act: 3.3132. Min Act: -0.0000

Data Index: 1099894 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.9563. Min Act: -0.0000

Data Index: 621364 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.8759. Min Act: -0.0001

Data Index: 125263 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.9758. Min Act: -0.0001

Data Index: 209017 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.7132. Min Act: -0.0000

Data Index: 120635 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.6855. Min Act: -0.0001

Data Index: 1302703 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.7805. Min Act: -0.0001

Data Index: 1138140 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.7596. Min Act: -0.0001

Data Index: 112360 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.5244. Min Act: -0.0001

Data Index: 182237 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.6367. Min Act: -0.0001

Data Index: 1251109 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.2834. Min Act: -0.0001

Data Index: 1190761 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.7376. Min Act: -0.0001

Data Index: 644319 (C4 (Web Text))

Max Activating Token Index: 148

Text #13

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.5982. Min Act: -0.0001

Data Index: 349198 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.5573. Min Act: -0.0001

Data Index: 56646 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.6552. Min Act: -0.0001

Data Index: 774090 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.1663. Min Act: -0.0001

Data Index: 266163 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.5056. Min Act: -0.0001

Data Index: 1317069 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.3333. Min Act: -0.0001

Data Index: 861220 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 3.3132. Min Range: -3.3132

Max Act: 2.3326. Min Act: -0.0001

Data Index: 155004 (C4 (Web Text))

Max Activating Token Index: 457