Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3011 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4687. Min Act: -0.0003

Data Index: 1030033 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4648. Min Act: -0.0003

Data Index: 640213 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4522. Min Act: -0.0003

Data Index: 37614 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.4169. Min Act: -0.0003

Data Index: 164860 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3877. Min Act: -0.0003

Data Index: 648948 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3787. Min Act: -0.0003

Data Index: 1049870 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3542. Min Act: -0.0003

Data Index: 983167 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3794. Min Act: -0.0003

Data Index: 1004081 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3626. Min Act: -0.0003

Data Index: 718695 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3755. Min Act: -0.0003

Data Index: 463325 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3740. Min Act: -0.0003

Data Index: 1200743 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3629. Min Act: -0.0003

Data Index: 793888 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3564. Min Act: -0.0003

Data Index: 416899 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3567. Min Act: -0.0003

Data Index: 1104859 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3551. Min Act: -0.0003

Data Index: 836146 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3547. Min Act: -0.0003

Data Index: 199976 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3513. Min Act: -0.0003

Data Index: 93126 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3523. Min Act: -0.0003

Data Index: 543211 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3622. Min Act: -0.0003

Data Index: 156579 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.4687. Min Range: -0.4687

Max Act: 0.3597. Min Act: -0.0003

Data Index: 1044809 (C4 (Web Text))

Max Activating Token Index: 784