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

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

Neuron 2190 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.5043. Min Range: -7.5043

Max Act: 7.5043. Min Act: -0.0000

Data Index: 448828 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 7.5043. Min Range: -7.5043

Max Act: 6.0469. Min Act: -0.0000

Data Index: 1080367 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.5897. Min Act: -0.0000

Data Index: 989976 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.0943. Min Act: -0.0000

Data Index: 506374 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.5978. Min Act: -0.0000

Data Index: 645881 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.3901. Min Act: -0.0000

Data Index: 915375 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.5776. Min Act: -0.0000

Data Index: 220027 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.7403. Min Act: -0.0000

Data Index: 183866 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.5267. Min Act: -0.0000

Data Index: 438409 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.3904. Min Act: -0.0000

Data Index: 569822 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.2301. Min Act: -0.0000

Data Index: 1121423 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 7.5043. Min Range: -7.5043

Max Act: 3.1499. Min Act: -0.0000

Data Index: 938356 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 7.5043. Min Range: -7.5043

Max Act: 3.9603. Min Act: -0.0000

Data Index: 1323584 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 7.5043. Min Range: -7.5043

Max Act: 3.9777. Min Act: -0.0000

Data Index: 170352 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 7.5043. Min Range: -7.5043

Max Act: 3.9402. Min Act: -0.0000

Data Index: 544190 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 7.5043. Min Range: -7.5043

Max Act: 3.9302. Min Act: -0.0000

Data Index: 781729 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.0036. Min Act: -0.0000

Data Index: 590923 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.2543. Min Act: -0.0000

Data Index: 452802 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 7.5043. Min Range: -7.5043

Max Act: 3.7093. Min Act: -0.0000

Data Index: 1221295 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 7.5043. Min Range: -7.5043

Max Act: 4.2009. Min Act: -0.0000

Data Index: 1152557 (C4 (Web Text))

Max Activating Token Index: 282