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

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

Neuron 3450 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: 0.3047. Min Range: -0.3047

Max Act: 0.2914. Min Act: -0.0001

Data Index: 497339 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2961. Min Act: -0.0000

Data Index: 960782 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1023709 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2868. Min Act: -0.0000

Data Index: 703066 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2660. Min Act: -0.0000

Data Index: 35486 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2709. Min Act: -0.0001

Data Index: 551320 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2806. Min Act: -0.0000

Data Index: 393354 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2526. Min Act: -0.0000

Data Index: 725918 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2706. Min Act: -0.0000

Data Index: 943723 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2848. Min Act: -0.0001

Data Index: 360779 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2615. Min Act: -0.0001

Data Index: 308061 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2587. Min Act: -0.0000

Data Index: 316902 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2658. Min Act: -0.0001

Data Index: 477255 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2515. Min Act: -0.0000

Data Index: 1068469 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2692. Min Act: -0.0001

Data Index: 263968 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2577. Min Act: -0.0000

Data Index: 211943 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1034529 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2592. Min Act: -0.0000

Data Index: 713672 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2214. Min Act: -0.0000

Data Index: 657370 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2466. Min Act: -0.0001

Data Index: 418943 (C4 (Web Text))

Max Activating Token Index: 62