Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4663 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.5163. Min Act: 0.0001

Data Index: 1269182 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3687. Min Act: 0.0000

Data Index: 727134 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3773. Min Act: -0.0000

Data Index: 637720 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3542. Min Act: -0.0000

Data Index: 878575 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3442. Min Act: -0.0000

Data Index: 594708 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3147. Min Act: 0.0000

Data Index: 283110 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3131. Min Act: -0.0000

Data Index: 71998 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1044805 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3036. Min Act: -0.0000

Data Index: 639970 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1054532 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2991. Min Act: -0.0000

Data Index: 716156 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2904. Min Act: 0.0000

Data Index: 574007 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2847. Min Act: -0.0000

Data Index: 425482 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2817. Min Act: 0.0000

Data Index: 118749 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2899. Min Act: -0.0000

Data Index: 809914 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2702. Min Act: -0.0000

Data Index: 800626 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2826. Min Act: 0.0001

Data Index: 1291809 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2718. Min Act: -0.0000

Data Index: 755814 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2709. Min Act: -0.0000

Data Index: 42175 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2855. Min Act: -0.0000

Data Index: 526170 (C4 (Web Text))

Max Activating Token Index: 1012