Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 884 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.3462. Min Act: -0.0000

Data Index: 471252 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1441284 (Python Code)

Max Activating Token Index: 416

Text #2

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1022898 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1247751 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2870. Min Act: -0.0000

Data Index: 858010 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.3032. Min Act: -0.0000

Data Index: 733507 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1584256 (Python Code)

Max Activating Token Index: 798

Text #7

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1104398 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1119968 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1043587 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1372309 (Python Code)

Max Activating Token Index: 997

Text #11

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2946. Min Act: -0.0000

Data Index: 20745 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2933. Min Act: -0.0000

Data Index: 156816 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2689. Min Act: -0.0001

Data Index: 1639862 (Python Code)

Max Activating Token Index: 668

Text #14

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2821. Min Act: -0.0000

Data Index: 148747 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2631. Min Act: -0.0000

Data Index: 708836 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1244606 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1655168 (Python Code)

Max Activating Token Index: 740

Text #18

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2601. Min Act: -0.0000

Data Index: 816312 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.3462. Min Range: -0.3462

Max Act: 0.2844. Min Act: -0.0000

Data Index: 298922 (C4 (Web Text))

Max Activating Token Index: 42