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

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

Neuron 2422 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.6493. Min Act: -0.0001

Data Index: 779188 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.5650. Min Act: -0.0001

Data Index: 878512 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4757. Min Act: -0.0001

Data Index: 892977 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4602. Min Act: -0.0001

Data Index: 1199147 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4542. Min Act: -0.0000

Data Index: 442529 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4179. Min Act: -0.0001

Data Index: 282044 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4111. Min Act: -0.0001

Data Index: 1078824 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4183. Min Act: -0.0000

Data Index: 928943 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4046. Min Act: -0.0001

Data Index: 1063033 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4016. Min Act: -0.0000

Data Index: 181706 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.3991. Min Act: -0.0000

Data Index: 417133 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.3972. Min Act: -0.0000

Data Index: 616465 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.4083. Min Act: -0.0001

Data Index: 779594 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.3716. Min Act: -0.0000

Data Index: 10761 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.3653. Min Act: -0.0001

Data Index: 307189 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.3506. Min Act: -0.0000

Data Index: 810459 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1026605 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.3603. Min Act: -0.0000

Data Index: 77156 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.3366. Min Act: -0.0000

Data Index: 279649 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.6493. Min Range: -0.6493

Max Act: 0.3597. Min Act: -0.0000

Data Index: 491011 (C4 (Web Text))

Max Activating Token Index: 483