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

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

Neuron 227 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.4730. Min Act: -0.0001

Data Index: 676644 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3843. Min Act: -0.0001

Data Index: 632956 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.4283. Min Act: -0.0001

Data Index: 1137343 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3912. Min Act: -0.0001

Data Index: 1305009 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3958. Min Act: -0.0001

Data Index: 196718 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3007. Min Act: -0.0001

Data Index: 603616 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3074. Min Act: -0.0001

Data Index: 391198 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2373. Min Act: -0.0001

Data Index: 329609 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2515. Min Act: -0.0000

Data Index: 380402 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2754. Min Act: -0.0001

Data Index: 762718 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2629. Min Act: -0.0001

Data Index: 139755 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1717. Min Act: -0.0001

Data Index: 483632 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1576. Min Act: -0.0001

Data Index: 367180 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2186. Min Act: -0.0001

Data Index: 1320249 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1104. Min Act: -0.0001

Data Index: 1263570 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1171. Min Act: -0.0001

Data Index: 1332899 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0673. Min Act: -0.0001

Data Index: 657140 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0475. Min Act: -0.0001

Data Index: 581261 (C4 (Web Text))

Max Activating Token Index: 456

Text #18

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0733. Min Act: -0.0001

Data Index: 763748 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.0268. Min Act: -0.0001

Data Index: 1096788 (C4 (Web Text))

Max Activating Token Index: 838