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

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

Neuron 3326 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0535. Min Range: -1.0535

Max Act: 1.0535. Min Act: -0.0001

Data Index: 837282 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.9104. Min Act: -0.0001

Data Index: 438122 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.8390. Min Act: -0.0000

Data Index: 434491 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1341997 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.8457. Min Act: -0.0000

Data Index: 58524 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1089608 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7532. Min Act: -0.0001

Data Index: 248080 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1078491 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.8372. Min Act: -0.0000

Data Index: 912532 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7371. Min Act: -0.0001

Data Index: 1230766 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.8047. Min Act: -0.0000

Data Index: 13467 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7165. Min Act: -0.0000

Data Index: 175504 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7504. Min Act: -0.0000

Data Index: 242997 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7526. Min Act: -0.0000

Data Index: 853817 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1358682 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7400. Min Act: -0.0000

Data Index: 944350 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7737. Min Act: -0.0001

Data Index: 29212 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1108471 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7145. Min Act: -0.0000

Data Index: 990780 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 1.0535. Min Range: -1.0535

Max Act: 0.7038. Min Act: -0.0000

Data Index: 591270 (C4 (Web Text))

Max Activating Token Index: 244