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

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

Neuron 6103 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.7280. Min Act: -0.0002

Data Index: 8644 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.4718. Min Act: -0.0002

Data Index: 924920 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.3911. Min Act: -0.0002

Data Index: 680956 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.4363. Min Act: -0.0002

Data Index: 829373 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.4174. Min Act: -0.0002

Data Index: 604576 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.3867. Min Act: -0.0002

Data Index: 322022 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.3414. Min Act: -0.0002

Data Index: 901270 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.1830. Min Act: -0.0002

Data Index: 973635 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.2596. Min Act: -0.0002

Data Index: 1336840 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.1804. Min Act: -0.0002

Data Index: 666013 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.1837. Min Act: -0.0002

Data Index: 631923 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.2215. Min Act: -0.0002

Data Index: 1295263 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.1290. Min Act: -0.0002

Data Index: 1194580 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.1080. Min Act: -0.0002

Data Index: 752506 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.1231. Min Act: -0.0002

Data Index: 566551 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.1622. Min Act: -0.0002

Data Index: 248467 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.1504. Min Act: -0.0002

Data Index: 1103982 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.1088. Min Act: -0.0002

Data Index: 840682 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.0788. Min Act: -0.0002

Data Index: 131080 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 2.7280. Min Range: -2.7280

Max Act: 2.0905. Min Act: -0.0002

Data Index: 556115 (C4 (Web Text))

Max Activating Token Index: 445