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

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

Neuron 928 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: 12.2198. Min Range: -12.2198

Max Act: 12.2198. Min Act: -0.0000

Data Index: 401915 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 12.2198. Min Range: -12.2198

Max Act: 10.8763. Min Act: -0.0000

Data Index: 936334 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 12.2198. Min Range: -12.2198

Max Act: 5.0541. Min Act: -0.0001

Data Index: 988857 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.5551. Min Act: -0.0000

Data Index: 436669 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3497. Min Act: -0.0000

Data Index: 873915 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.4348. Min Act: -0.0001

Data Index: 1018673 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.4175. Min Act: -0.0001

Data Index: 755317 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3380. Min Act: -0.0000

Data Index: 789091 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.4343. Min Act: -0.0001

Data Index: 1606442 (Python Code)

Max Activating Token Index: 260

Text #9

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3739. Min Act: -0.0001

Data Index: 976812 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3023. Min Act: -0.0000

Data Index: 373799 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3443. Min Act: -0.0001

Data Index: 1485612 (Python Code)

Max Activating Token Index: 786

Text #12

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3583. Min Act: -0.0001

Data Index: 691072 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3275. Min Act: -0.0001

Data Index: 275999 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3517. Min Act: -0.0001

Data Index: 75115 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.2951. Min Act: -0.0001

Data Index: 896072 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3172. Min Act: -0.0001

Data Index: 501227 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3251. Min Act: -0.0000

Data Index: 891218 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1242919 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 12.2198. Min Range: -12.2198

Max Act: 0.3372. Min Act: -0.0001

Data Index: 1073468 (C4 (Web Text))

Max Activating Token Index: 937