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

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

Neuron 72 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1055. Min Range: -1.1055

Max Act: 1.1055. Min Act: -0.0001

Data Index: 93168 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 1.1055. Min Range: -1.1055

Max Act: 1.0715. Min Act: -0.0001

Data Index: 399008 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7907. Min Act: -0.0001

Data Index: 710919 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.8222. Min Act: -0.0001

Data Index: 898486 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7600. Min Act: -0.0001

Data Index: 1163604 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7144. Min Act: -0.0001

Data Index: 873082 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.7368. Min Act: -0.0001

Data Index: 1116758 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6908. Min Act: -0.0001

Data Index: 1120624 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6671. Min Act: -0.0001

Data Index: 1116232 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6814. Min Act: -0.0001

Data Index: 1198879 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6837. Min Act: -0.0001

Data Index: 345678 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6777. Min Act: -0.0001

Data Index: 908355 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6840. Min Act: -0.0001

Data Index: 82716 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6145. Min Act: -0.0001

Data Index: 1018592 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6442. Min Act: -0.0001

Data Index: 859370 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6440. Min Act: -0.0001

Data Index: 802269 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6261. Min Act: -0.0001

Data Index: 336607 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6410. Min Act: -0.0001

Data Index: 1188771 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6574. Min Act: -0.0001

Data Index: 863076 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 1.1055. Min Range: -1.1055

Max Act: 0.6742. Min Act: -0.0001

Data Index: 1050704 (C4 (Web Text))

Max Activating Token Index: 828