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

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

Neuron 1456 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.5716. Min Act: -0.0003

Data Index: 228377 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.5025. Min Act: -0.0002

Data Index: 1293702 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.3760. Min Act: -0.0003

Data Index: 1317008 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.3870. Min Act: -0.0002

Data Index: 564055 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.3471. Min Act: -0.0003

Data Index: 949253 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.4090. Min Act: -0.0002

Data Index: 1305496 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.2159. Min Act: -0.0002

Data Index: 839508 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.4294. Min Act: -0.0003

Data Index: 67799 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.4219. Min Act: -0.0002

Data Index: 1041875 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.3081. Min Act: -0.0002

Data Index: 1277564 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.2975. Min Act: -0.0003

Data Index: 43515 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.3324. Min Act: -0.0003

Data Index: 974833 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.2833. Min Act: -0.0003

Data Index: 446639 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.3040. Min Act: -0.0003

Data Index: 873857 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.0396. Min Act: -0.0002

Data Index: 731262 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.2607. Min Act: -0.0002

Data Index: 1028964 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.2673. Min Act: -0.0003

Data Index: 990307 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.2836. Min Act: -0.0002

Data Index: 309372 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.2484. Min Act: -0.0003

Data Index: 243630 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.5716. Min Range: -1.5716

Max Act: 1.2575. Min Act: -0.0002

Data Index: 771812 (C4 (Web Text))

Max Activating Token Index: 502