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

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

Neuron 3900 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.2455. Min Act: -0.0000

Data Index: 758104 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 1.2455. Min Range: -1.2455

Max Act: 1.0027. Min Act: -0.0000

Data Index: 1148049 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1229627 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.9543. Min Act: -0.0000

Data Index: 617073 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1253308 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8525. Min Act: -0.0000

Data Index: 369861 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8413. Min Act: -0.0000

Data Index: 754616 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8525. Min Act: -0.0000

Data Index: 666501 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8348. Min Act: -0.0000

Data Index: 167073 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.8037. Min Act: -0.0000

Data Index: 19545 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7488. Min Act: -0.0000

Data Index: 750608 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1338830 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7595. Min Act: -0.0000

Data Index: 625284 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7887. Min Act: -0.0000

Data Index: 776799 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1065823 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7956. Min Act: -0.0000

Data Index: 694461 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7695. Min Act: -0.0000

Data Index: 426698 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7670. Min Act: -0.0000

Data Index: 934475 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1048380 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 1.2455. Min Range: -1.2455

Max Act: 0.7304. Min Act: -0.0000

Data Index: 446012 (C4 (Web Text))

Max Activating Token Index: 703