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

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

Neuron 1346 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: 3.4131. Min Range: -3.4131

Max Act: 3.4131. Min Act: -0.0001

Data Index: 1185210 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 3.4131. Min Range: -3.4131

Max Act: 3.2200. Min Act: -0.0001

Data Index: 1225323 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.8063. Min Act: -0.0001

Data Index: 50614 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.8603. Min Act: -0.0001

Data Index: 1172658 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.6450. Min Act: -0.0001

Data Index: 400259 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.5554. Min Act: -0.0000

Data Index: 555845 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.7336. Min Act: -0.0001

Data Index: 440137 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.4167. Min Act: -0.0001

Data Index: 691345 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.4768. Min Act: -0.0001

Data Index: 94810 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.4129. Min Act: -0.0000

Data Index: 177757 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.2949. Min Act: -0.0001

Data Index: 929828 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.4148. Min Act: -0.0001

Data Index: 861010 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.5257. Min Act: -0.0001

Data Index: 696492 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.2661. Min Act: -0.0001

Data Index: 101831 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.5259. Min Act: -0.0001

Data Index: 1099565 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.2638. Min Act: -0.0001

Data Index: 141867 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.3723. Min Act: -0.0001

Data Index: 269960 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.5623. Min Act: -0.0001

Data Index: 528079 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.2906. Min Act: -0.0001

Data Index: 36667 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 3.4131. Min Range: -3.4131

Max Act: 2.2742. Min Act: -0.0001

Data Index: 204817 (C4 (Web Text))

Max Activating Token Index: 195