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

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

Neuron 3131 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.9172. Min Act: -0.0000

Data Index: 1003162 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.7301. Min Act: -0.0000

Data Index: 546240 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.6036. Min Act: -0.0000

Data Index: 894497 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.4843. Min Act: -0.0000

Data Index: 366667 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.4963. Min Act: -0.0000

Data Index: 1309143 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.4524. Min Act: -0.0000

Data Index: 464759 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.3613. Min Act: -0.0000

Data Index: 1460463 (Python Code)

Max Activating Token Index: 352

Text #7

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.2739. Min Act: -0.0000

Data Index: 1048410 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.3769. Min Act: -0.0000

Data Index: 74162 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.2606. Min Act: -0.0000

Data Index: 7409 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.3602. Min Act: -0.0000

Data Index: 145864 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.3144. Min Act: -0.0000

Data Index: 300064 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.3370. Min Act: -0.0001

Data Index: 190070 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.1823. Min Act: -0.0000

Data Index: 1071457 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.2120. Min Act: -0.0000

Data Index: 625625 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1190352 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.1507. Min Act: -0.0000

Data Index: 1194465 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1208008 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.1763. Min Act: -0.0000

Data Index: 395149 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 1.9172. Min Range: -1.9172

Max Act: 1.1419. Min Act: -0.0000

Data Index: 1123926 (C4 (Web Text))

Max Activating Token Index: 597