Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3001 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2799. Min Act: -0.0001

Data Index: 596651 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2633. Min Act: -0.0001

Data Index: 1093200 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2624. Min Act: -0.0001

Data Index: 544869 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2465. Min Act: -0.0000

Data Index: 470313 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2521. Min Act: -0.0000

Data Index: 251908 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2594. Min Act: -0.0001

Data Index: 433221 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2426. Min Act: -0.0001

Data Index: 658135 (C4 (Web Text))

Max Activating Token Index: 793

Text #7

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2463. Min Act: -0.0001

Data Index: 1154174 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2400. Min Act: -0.0001

Data Index: 1253196 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2467. Min Act: -0.0001

Data Index: 767340 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2441. Min Act: -0.0001

Data Index: 519258 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2449. Min Act: -0.0001

Data Index: 690770 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2431. Min Act: 0.0000

Data Index: 1120087 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2395. Min Act: -0.0001

Data Index: 403893 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2316. Min Act: -0.0001

Data Index: 310100 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2491. Min Act: -0.0001

Data Index: 634164 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2289. Min Act: -0.0001

Data Index: 661813 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2374. Min Act: -0.0001

Data Index: 1239041 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2279. Min Act: -0.0001

Data Index: 453512 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2256. Min Act: -0.0001

Data Index: 1170711 (C4 (Web Text))

Max Activating Token Index: 423