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

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

Neuron 2506 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: 0.7968. Min Range: -0.7968

Max Act: 0.7968. Min Act: -0.0001

Data Index: 1295621 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6877. Min Act: -0.0001

Data Index: 736787 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6805. Min Act: -0.0000

Data Index: 892683 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6479. Min Act: -0.0000

Data Index: 428565 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6869. Min Act: -0.0001

Data Index: 148160 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.7589. Min Act: -0.0001

Data Index: 285025 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6624. Min Act: -0.0001

Data Index: 74728 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6404. Min Act: -0.0000

Data Index: 429287 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1055996 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5783. Min Act: -0.0000

Data Index: 180150 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.6029. Min Act: -0.0001

Data Index: 319056 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5598. Min Act: -0.0000

Data Index: 746694 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5549. Min Act: -0.0001

Data Index: 455992 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5498. Min Act: -0.0001

Data Index: 140596 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5694. Min Act: -0.0001

Data Index: 557130 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5661. Min Act: -0.0001

Data Index: 1266678 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5283. Min Act: -0.0000

Data Index: 858200 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5366. Min Act: -0.0000

Data Index: 312604 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5364. Min Act: -0.0001

Data Index: 197603 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.7968. Min Range: -0.7968

Max Act: 0.5521. Min Act: -0.0000

Data Index: 744844 (C4 (Web Text))

Max Activating Token Index: 491