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

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

Neuron 3358 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: 1.7347. Min Range: -1.7347

Max Act: 1.7347. Min Act: -0.0000

Data Index: 228480 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.6429. Min Act: -0.0001

Data Index: 889262 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.6241. Min Act: -0.0000

Data Index: 121909 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.5988. Min Act: -0.0000

Data Index: 734889 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.6266. Min Act: -0.0001

Data Index: 907734 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.6282. Min Act: -0.0001

Data Index: 362763 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.6182. Min Act: -0.0000

Data Index: 755180 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.5763. Min Act: -0.0000

Data Index: 1308674 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.5710. Min Act: -0.0000

Data Index: 1349412 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.5726. Min Act: -0.0000

Data Index: 812168 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.4455. Min Act: -0.0001

Data Index: 740677 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.4464. Min Act: -0.0000

Data Index: 952937 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.6112. Min Act: -0.0001

Data Index: 338942 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.5119. Min Act: -0.0001

Data Index: 878662 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.4860. Min Act: -0.0001

Data Index: 159144 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.4765. Min Act: -0.0001

Data Index: 13163 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.3863. Min Act: -0.0000

Data Index: 265690 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.3869. Min Act: -0.0001

Data Index: 795053 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1339383 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 1.7347. Min Range: -1.7347

Max Act: 1.4593. Min Act: -0.0001

Data Index: 939886 (C4 (Web Text))

Max Activating Token Index: 132