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

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

Neuron 3800 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: 0.0573. Min Range: -0.0573

Max Act: 0.0573. Min Act: -0.0001

Data Index: 429304 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0557. Min Act: -0.0000

Data Index: 60225 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1272797 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0498. Min Act: -0.0001

Data Index: 917385 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1310730 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1200044 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0443. Min Act: -0.0001

Data Index: 1353889 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0434. Min Act: -0.0001

Data Index: 272094 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0417. Min Act: -0.0001

Data Index: 985906 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0428. Min Act: -0.0001

Data Index: 1080105 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0413. Min Act: -0.0001

Data Index: 405584 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1099118 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1781 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0408. Min Act: -0.0001

Data Index: 948530 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1342116 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1321793 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0372. Min Act: -0.0001

Data Index: 413551 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0381. Min Act: -0.0001

Data Index: 163914 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0365. Min Act: -0.0001

Data Index: 934964 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0372. Min Act: -0.0001

Data Index: 850067 (C4 (Web Text))

Max Activating Token Index: 417