Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2835 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.4284. Min Act: -0.0001

Data Index: 561861 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3907. Min Act: -0.0001

Data Index: 792068 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.4045. Min Act: -0.0001

Data Index: 450524 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3903. Min Act: -0.0001

Data Index: 1279652 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.4003. Min Act: -0.0001

Data Index: 1357250 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3874. Min Act: -0.0001

Data Index: 900548 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3936. Min Act: -0.0001

Data Index: 507525 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3897. Min Act: -0.0001

Data Index: 62014 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3771. Min Act: -0.0001

Data Index: 1350336 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3668. Min Act: -0.0001

Data Index: 21480 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3766. Min Act: -0.0001

Data Index: 18301 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3818. Min Act: -0.0001

Data Index: 1155347 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3673. Min Act: -0.0001

Data Index: 1031009 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3647. Min Act: -0.0001

Data Index: 738101 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3629. Min Act: -0.0001

Data Index: 1206770 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3477. Min Act: -0.0001

Data Index: 378856 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3721. Min Act: -0.0001

Data Index: 606299 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3698. Min Act: -0.0001

Data Index: 374131 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3583. Min Act: -0.0001

Data Index: 39240 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.4284. Min Range: -0.4284

Max Act: 0.3440. Min Act: -0.0001

Data Index: 1053822 (C4 (Web Text))

Max Activating Token Index: 380