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

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

Neuron 3848 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: 2.7242. Min Range: -2.7242

Max Act: 2.7242. Min Act: -0.0001

Data Index: 162888 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.5761. Min Act: -0.0000

Data Index: 153525 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.6830. Min Act: -0.0001

Data Index: 1340549 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.5157. Min Act: -0.0000

Data Index: 44066 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.4565. Min Act: -0.0001

Data Index: 1327451 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.5786. Min Act: -0.0000

Data Index: 269014 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.4286. Min Act: -0.0000

Data Index: 68200 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.1640. Min Act: -0.0000

Data Index: 904603 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.4182. Min Act: -0.0001

Data Index: 431788 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.2918. Min Act: -0.0000

Data Index: 150193 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.2794. Min Act: -0.0001

Data Index: 388107 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.3952. Min Act: -0.0001

Data Index: 459225 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.2638. Min Act: -0.0000

Data Index: 919998 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.2381. Min Act: -0.0001

Data Index: 1252054 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.2503. Min Act: -0.0001

Data Index: 749735 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.2343. Min Act: -0.0001

Data Index: 221567 (C4 (Web Text))

Max Activating Token Index: 971

Text #16

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.2291. Min Act: -0.0000

Data Index: 1039478 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.2126. Min Act: -0.0001

Data Index: 673821 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.2120. Min Act: -0.0000

Data Index: 841878 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 2.7242. Min Range: -2.7242

Max Act: 2.2022. Min Act: -0.0000

Data Index: 755866 (C4 (Web Text))

Max Activating Token Index: 987