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

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

Neuron 4408 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: 0.9803. Min Range: -0.9803

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1131223 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.9470. Min Act: -0.0000

Data Index: 443523 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.9300. Min Act: -0.0000

Data Index: 538218 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.9803. Min Act: -0.0000

Data Index: 750094 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8257. Min Act: -0.0000

Data Index: 409029 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1114893 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.8244. Min Act: -0.0000

Data Index: 1301591 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1330085 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7768. Min Act: -0.0000

Data Index: 786042 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7244. Min Act: -0.0000

Data Index: 1219127 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7492. Min Act: -0.0000

Data Index: 418654 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1316219 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6955. Min Act: -0.0000

Data Index: 598469 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7176. Min Act: -0.0000

Data Index: 416218 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1260276 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6217. Min Act: -0.0000

Data Index: 956934 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6948. Min Act: -0.0000

Data Index: 167854 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1250054 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6620. Min Act: -0.0000

Data Index: 94727 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.9803. Min Range: -0.9803

Max Act: 0.6427. Min Act: -0.0000

Data Index: 3959 (C4 (Web Text))

Max Activating Token Index: 571