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

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

Neuron 1360 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1193. Min Range: -2.1193

Max Act: 2.1193. Min Act: -0.0000

Data Index: 1192406 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.9213. Min Act: -0.0000

Data Index: 174855 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.9098. Min Act: -0.0000

Data Index: 853979 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.7336. Min Act: -0.0000

Data Index: 714009 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.8139. Min Act: -0.0000

Data Index: 1140367 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.7064. Min Act: -0.0000

Data Index: 352825 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.4514. Min Act: -0.0000

Data Index: 1297147 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.5332. Min Act: -0.0000

Data Index: 216826 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.4452. Min Act: -0.0000

Data Index: 755829 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.3471. Min Act: -0.0000

Data Index: 1194386 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.4096. Min Act: -0.0000

Data Index: 806229 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.4076. Min Act: -0.0000

Data Index: 989958 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.4805. Min Act: -0.0000

Data Index: 1163398 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.3922. Min Act: -0.0000

Data Index: 1221560 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.2938. Min Act: -0.0000

Data Index: 1050459 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.3453. Min Act: -0.0000

Data Index: 45240 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1012715 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.2562. Min Act: -0.0000

Data Index: 639692 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.3436. Min Act: -0.0000

Data Index: 662897 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 2.1193. Min Range: -2.1193

Max Act: 1.2546. Min Act: -0.0000

Data Index: 893625 (C4 (Web Text))

Max Activating Token Index: 886