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

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

Neuron 3571 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1084066 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7593. Min Act: -0.0000

Data Index: 359360 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7514. Min Act: -0.0000

Data Index: 84034 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7008. Min Act: -0.0001

Data Index: 9778 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1206483 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6806. Min Act: -0.0000

Data Index: 699412 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6865. Min Act: -0.0000

Data Index: 489801 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6545. Min Act: -0.0000

Data Index: 114738 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1223446 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6947. Min Act: -0.0000

Data Index: 813373 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6704. Min Act: -0.0000

Data Index: 790556 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6645. Min Act: -0.0000

Data Index: 328772 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.7004. Min Act: -0.0000

Data Index: 782624 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6177. Min Act: -0.0000

Data Index: 564417 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6605. Min Act: -0.0001

Data Index: 218995 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6809. Min Act: -0.0000

Data Index: 645649 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6605. Min Act: -0.0000

Data Index: 860090 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1139689 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6502. Min Act: -0.0000

Data Index: 857644 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.7697. Min Range: -0.7697

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1014540 (C4 (Web Text))

Max Activating Token Index: 75