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

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

Neuron 5683 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.6107. Min Act: -0.0002

Data Index: 577302 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.5978. Min Act: -0.0002

Data Index: 468921 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.5705. Min Act: -0.0002

Data Index: 1345560 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.5328. Min Act: -0.0002

Data Index: 769586 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.5736. Min Act: -0.0002

Data Index: 528173 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.5521. Min Act: -0.0002

Data Index: 1185976 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.4792. Min Act: -0.0002

Data Index: 878283 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.5064. Min Act: -0.0002

Data Index: 259648 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.4853. Min Act: -0.0002

Data Index: 831821 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.4648. Min Act: -0.0002

Data Index: 434681 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.4904. Min Act: -0.0002

Data Index: 641772 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.4482. Min Act: -0.0002

Data Index: 1145042 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.4299. Min Act: -0.0002

Data Index: 81671 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.4398. Min Act: -0.0002

Data Index: 498115 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.3815. Min Act: -0.0002

Data Index: 341418 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.4261. Min Act: -0.0002

Data Index: 1311149 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.3901. Min Act: -0.0002

Data Index: 409664 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.4108. Min Act: -0.0002

Data Index: 784518 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.3993. Min Act: -0.0002

Data Index: 1296017 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.6107. Min Range: -0.6107

Max Act: 0.3667. Min Act: -0.0002

Data Index: 897555 (C4 (Web Text))

Max Activating Token Index: 261