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

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

Neuron 1734 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: 3.6276. Min Range: -3.6276

Max Act: 3.5357. Min Act: -0.0000

Data Index: 763010 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 3.6276. Min Range: -3.6276

Max Act: 3.6276. Min Act: -0.0000

Data Index: 1146585 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 3.6276. Min Range: -3.6276

Max Act: 3.5936. Min Act: -0.0000

Data Index: 20102 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 3.6276. Min Range: -3.6276

Max Act: 3.0852. Min Act: -0.0000

Data Index: 1145721 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.8111. Min Act: -0.0000

Data Index: 775704 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.8559. Min Act: -0.0000

Data Index: 1064706 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.9420. Min Act: -0.0000

Data Index: 1165213 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.6078. Min Act: -0.0000

Data Index: 1320796 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.7362. Min Act: -0.0000

Data Index: 941000 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.8399. Min Act: -0.0000

Data Index: 2310 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.9234. Min Act: -0.0000

Data Index: 1117278 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.9339. Min Act: -0.0000

Data Index: 844816 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.7510. Min Act: -0.0000

Data Index: 1330115 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.7532. Min Act: -0.0000

Data Index: 1228652 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.6761. Min Act: -0.0000

Data Index: 372072 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.6806. Min Act: -0.0000

Data Index: 487742 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 3.6276. Min Range: -3.6276

Max Act: 3.0401. Min Act: -0.0000

Data Index: 1235593 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.6106. Min Act: -0.0000

Data Index: 752609 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.7169. Min Act: -0.0000

Data Index: 782921 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 3.6276. Min Range: -3.6276

Max Act: 2.4276. Min Act: -0.0000

Data Index: 178695 (C4 (Web Text))

Max Activating Token Index: 973