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

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

Neuron 841 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8400. Min Act: -0.0000

Data Index: 277644 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8320. Min Act: -0.0000

Data Index: 305773 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8471. Min Act: -0.0000

Data Index: 939004 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8427. Min Act: -0.0000

Data Index: 485876 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8861. Min Act: -0.0000

Data Index: 355367 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1124486 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8514. Min Act: -0.0000

Data Index: 49214 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7853. Min Act: -0.0000

Data Index: 672002 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8081. Min Act: -0.0000

Data Index: 588859 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8785. Min Act: -0.0000

Data Index: 791794 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8214. Min Act: -0.0000

Data Index: 474408 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7796. Min Act: -0.0000

Data Index: 883624 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7744. Min Act: -0.0000

Data Index: 755530 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7490. Min Act: -0.0000

Data Index: 1298776 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7983. Min Act: -0.0000

Data Index: 845060 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7663. Min Act: -0.0000

Data Index: 999358 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1229010 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.8256. Min Act: -0.0000

Data Index: 742973 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7817. Min Act: -0.0000

Data Index: 782219 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.8861. Min Range: -0.8861

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1263456 (C4 (Web Text))

Max Activating Token Index: 53