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

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

Neuron 3881 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3971. Min Act: -0.0000

Data Index: 735965 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3596. Min Act: -0.0000

Data Index: 195323 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1116534 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3093. Min Act: -0.0000

Data Index: 917038 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2870. Min Act: -0.0000

Data Index: 1022942 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2775. Min Act: -0.0000

Data Index: 75194 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1186713 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2926. Min Act: -0.0000

Data Index: 824241 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2768. Min Act: -0.0000

Data Index: 684676 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2689. Min Act: -0.0000

Data Index: 658334 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3219. Min Act: -0.0000

Data Index: 51595 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2865. Min Act: -0.0000

Data Index: 970983 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2655. Min Act: -0.0000

Data Index: 577446 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1355241 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2817. Min Act: -0.0000

Data Index: 363654 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1148160 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2802. Min Act: -0.0000

Data Index: 952943 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2680. Min Act: -0.0000

Data Index: 586843 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2783. Min Act: -0.0000

Data Index: 639023 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2932. Min Act: -0.0000

Data Index: 762604 (C4 (Web Text))

Max Activating Token Index: 223