Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 34 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.5749. Min Act: -0.0001

Data Index: 340254 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.5699. Min Act: -0.0001

Data Index: 362461 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.5066. Min Act: -0.0001

Data Index: 795241 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4934. Min Act: -0.0001

Data Index: 272484 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4549. Min Act: -0.0001

Data Index: 343889 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4729. Min Act: -0.0001

Data Index: 269001 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4472. Min Act: -0.0001

Data Index: 1441697 (Python Code)

Max Activating Token Index: 267

Text #7

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4424. Min Act: -0.0001

Data Index: 181364 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4423. Min Act: -0.0001

Data Index: 1491773 (Python Code)

Max Activating Token Index: 929

Text #9

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4031. Min Act: -0.0001

Data Index: 1391694 (Python Code)

Max Activating Token Index: 637

Text #10

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4412. Min Act: -0.0001

Data Index: 264115 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4424. Min Act: -0.0001

Data Index: 1648119 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4277. Min Act: -0.0001

Data Index: 965243 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.3915. Min Act: -0.0001

Data Index: 1383837 (Python Code)

Max Activating Token Index: 790

Text #14

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.3904. Min Act: -0.0001

Data Index: 1430985 (Python Code)

Max Activating Token Index: 175

Text #15

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4114. Min Act: -0.0001

Data Index: 751986 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.3884. Min Act: -0.0001

Data Index: 1464786 (Python Code)

Max Activating Token Index: 287

Text #17

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4090. Min Act: -0.0001

Data Index: 756844 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4234. Min Act: -0.0001

Data Index: 1446747 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 0.5749. Min Range: -0.5749

Max Act: 0.4081. Min Act: -0.0001

Data Index: 1520543 (Python Code)

Max Activating Token Index: 65