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

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

Neuron 2721 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.7277. Min Act: -0.0000

Data Index: 1073792 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.9333. Min Act: -0.0000

Data Index: 242015 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.9139. Min Act: -0.0001

Data Index: 98358 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.7439. Min Act: -0.0001

Data Index: 325278 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.8651. Min Act: -0.0001

Data Index: 179488 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.8466. Min Act: -0.0001

Data Index: 482109 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 3.0952. Min Range: -3.0952

Max Act: 3.0952. Min Act: -0.0000

Data Index: 1296220 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.6725. Min Act: -0.0000

Data Index: 20610 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.7809. Min Act: -0.0001

Data Index: 240907 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.5786. Min Act: -0.0001

Data Index: 735920 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.6864. Min Act: -0.0001

Data Index: 266012 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.7762. Min Act: -0.0000

Data Index: 176922 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.6253. Min Act: -0.0001

Data Index: 607500 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.4675. Min Act: -0.0001

Data Index: 468555 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.3288. Min Act: -0.0000

Data Index: 968291 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.5675. Min Act: -0.0001

Data Index: 718035 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.2782. Min Act: -0.0001

Data Index: 324269 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.2834. Min Act: -0.0001

Data Index: 1108377 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.2300. Min Act: -0.0001

Data Index: 511049 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 3.0952. Min Range: -3.0952

Max Act: 2.2145. Min Act: -0.0000

Data Index: 582263 (C4 (Web Text))

Max Activating Token Index: 565