Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4754 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.1177. Min Range: -3.1177

Max Act: 3.1177. Min Act: -0.0000

Data Index: 451695 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.5138. Min Act: -0.0000

Data Index: 1232455 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.6087. Min Act: -0.0000

Data Index: 1027776 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.5632. Min Act: -0.0000

Data Index: 154162 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.4206. Min Act: -0.0000

Data Index: 1345241 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.4352. Min Act: -0.0000

Data Index: 384660 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.3377. Min Act: -0.0000

Data Index: 1001155 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.2869. Min Act: -0.0000

Data Index: 705772 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.3664. Min Act: -0.0000

Data Index: 1008116 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.3318. Min Act: -0.0000

Data Index: 655392 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.3433. Min Act: -0.0000

Data Index: 1350235 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.2881. Min Act: -0.0000

Data Index: 456815 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.1571. Min Act: -0.0000

Data Index: 317765 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.5154. Min Act: -0.0000

Data Index: 42683 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.2728. Min Act: -0.0000

Data Index: 342112 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.2492. Min Act: -0.0000

Data Index: 989807 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.2382. Min Act: -0.0000

Data Index: 1246497 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.2685. Min Act: -0.0000

Data Index: 760546 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 3.1177. Min Range: -3.1177

Max Act: 1.8222. Min Act: -0.0000

Data Index: 117534 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 3.1177. Min Range: -3.1177

Max Act: 2.0747. Min Act: -0.0000

Data Index: 935922 (C4 (Web Text))

Max Activating Token Index: 90