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

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

Neuron 2339 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1067412 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.5019. Min Act: 0.0000

Data Index: 26609 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4616. Min Act: -0.0001

Data Index: 526074 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1331196 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4473. Min Act: -0.0000

Data Index: 1285789 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4582. Min Act: -0.0000

Data Index: 755439 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4393. Min Act: -0.0000

Data Index: 571066 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1078682 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3992. Min Act: -0.0000

Data Index: 842971 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3969. Min Act: -0.0000

Data Index: 474409 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3796. Min Act: -0.0001

Data Index: 31108 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3751. Min Act: -0.0000

Data Index: 643634 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3732. Min Act: -0.0000

Data Index: 176445 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3551. Min Act: -0.0000

Data Index: 784158 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1072611 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3408. Min Act: -0.0000

Data Index: 1210 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3873. Min Act: -0.0000

Data Index: 189324 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3452. Min Act: -0.0001

Data Index: 748199 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3468. Min Act: -0.0000

Data Index: 727203 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.6055. Min Range: -0.6055

Max Act: 0.3333. Min Act: -0.0000

Data Index: 63511 (C4 (Web Text))

Max Activating Token Index: 909