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

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

Neuron 961 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.4906. Min Act: -0.0002

Data Index: 614039 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.4533. Min Act: -0.0002

Data Index: 332309 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.4105. Min Act: -0.0002

Data Index: 33340 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3652. Min Act: -0.0001

Data Index: 37079 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3753. Min Act: -0.0002

Data Index: 637280 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.4794. Min Act: -0.0001

Data Index: 955648 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.4775. Min Act: -0.0002

Data Index: 250852 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3379. Min Act: -0.0001

Data Index: 1332324 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3636. Min Act: -0.0001

Data Index: 986928 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3925. Min Act: -0.0001

Data Index: 546854 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3117. Min Act: -0.0002

Data Index: 509821 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3026. Min Act: -0.0002

Data Index: 61975 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2948. Min Act: -0.0001

Data Index: 282650 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3322. Min Act: -0.0001

Data Index: 3544 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3279. Min Act: -0.0001

Data Index: 757563 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2567. Min Act: -0.0002

Data Index: 17654 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3202. Min Act: -0.0001

Data Index: 186109 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3106. Min Act: -0.0001

Data Index: 483016 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.3038. Min Act: -0.0001

Data Index: 523322 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 1.4906. Min Range: -1.4906

Max Act: 1.2639. Min Act: -0.0001

Data Index: 1327466 (C4 (Web Text))

Max Activating Token Index: 910