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

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

Neuron 1983 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0578. Min Act: -0.0001

Data Index: 840544 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0596. Min Act: -0.0001

Data Index: 673207 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0547. Min Act: -0.0001

Data Index: 933017 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0530. Min Act: -0.0001

Data Index: 653536 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0502. Min Act: -0.0001

Data Index: 524202 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0519. Min Act: -0.0001

Data Index: 480377 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0502. Min Act: -0.0001

Data Index: 429704 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0499. Min Act: -0.0001

Data Index: 419386 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0496. Min Act: -0.0001

Data Index: 1145352 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0481. Min Act: -0.0001

Data Index: 417396 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0544. Min Act: -0.0001

Data Index: 729844 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0461. Min Act: -0.0001

Data Index: 75895 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1280043 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1184985 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0481. Min Act: -0.0001

Data Index: 764159 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0462. Min Act: -0.0001

Data Index: 868580 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1992 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1547555 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1347018 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0433. Min Act: -0.0001

Data Index: 426058 (C4 (Web Text))

Max Activating Token Index: 498