Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2375 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.9340. Min Range: -2.9340

Max Act: 2.9340. Min Act: -0.0000

Data Index: 304798 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 2.9340. Min Range: -2.9340

Max Act: 2.1465. Min Act: -0.0001

Data Index: 1261595 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 2.9340. Min Range: -2.9340

Max Act: 2.0195. Min Act: -0.0001

Data Index: 1117859 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.8428. Min Act: -0.0001

Data Index: 284089 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.7773. Min Act: -0.0001

Data Index: 50784 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.8483. Min Act: -0.0001

Data Index: 264675 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.9196. Min Act: -0.0000

Data Index: 744730 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.7277. Min Act: -0.0001

Data Index: 67821 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.6630. Min Act: -0.0001

Data Index: 309554 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.8232. Min Act: -0.0000

Data Index: 620908 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.7010. Min Act: -0.0001

Data Index: 805828 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.6009. Min Act: -0.0001

Data Index: 667408 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.5583. Min Act: -0.0001

Data Index: 1236314 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.6224. Min Act: -0.0000

Data Index: 262977 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.5441. Min Act: -0.0000

Data Index: 1095563 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.6131. Min Act: -0.0001

Data Index: 980973 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.6063. Min Act: -0.0000

Data Index: 805807 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.4973. Min Act: -0.0001

Data Index: 935524 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.4787. Min Act: -0.0001

Data Index: 410126 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 2.9340. Min Range: -2.9340

Max Act: 1.4652. Min Act: -0.0001

Data Index: 346145 (C4 (Web Text))

Max Activating Token Index: 682