Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3830 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.5516. Min Act: -0.0000

Data Index: 693717 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1285683 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4485. Min Act: -0.0000

Data Index: 861936 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4385. Min Act: -0.0000

Data Index: 965236 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1080986 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1205153 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4355. Min Act: -0.0000

Data Index: 858186 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1337428 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4436. Min Act: -0.0001

Data Index: 770590 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1004608 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1221279 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.3965. Min Act: -0.0001

Data Index: 1213457 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1100591 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.3811. Min Act: -0.0001

Data Index: 243229 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.4079. Min Act: -0.0000

Data Index: 660851 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.3592. Min Act: -0.0000

Data Index: 334991 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.3947. Min Act: 0.0000

Data Index: 703967 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.3696. Min Act: -0.0000

Data Index: 450709 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.3747. Min Act: -0.0000

Data Index: 279312 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.5516. Min Range: -0.5516

Max Act: 0.3816. Min Act: -0.0000

Data Index: 1046650 (C4 (Web Text))

Max Activating Token Index: 609