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

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

Neuron 1130 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: 0.3866. Min Range: -0.3866

Max Act: 0.3866. Min Act: -0.0000

Data Index: 241748 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3724. Min Act: -0.0001

Data Index: 154379 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3594. Min Act: -0.0001

Data Index: 1299518 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3383. Min Act: -0.0000

Data Index: 503678 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3471. Min Act: -0.0000

Data Index: 342183 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3342. Min Act: -0.0000

Data Index: 137985 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3313. Min Act: -0.0000

Data Index: 1067520 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3261. Min Act: -0.0000

Data Index: 11857 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3386. Min Act: -0.0001

Data Index: 191 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3124. Min Act: -0.0001

Data Index: 1051474 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3354. Min Act: -0.0000

Data Index: 673764 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3307. Min Act: -0.0001

Data Index: 1256069 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3307. Min Act: -0.0000

Data Index: 1031589 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3202. Min Act: -0.0000

Data Index: 574376 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3398. Min Act: -0.0001

Data Index: 1238304 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1248419 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3310. Min Act: -0.0001

Data Index: 1456063 (Python Code)

Max Activating Token Index: 430

Text #17

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3093. Min Act: -0.0001

Data Index: 993919 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3177. Min Act: -0.0001

Data Index: 27942 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.3866. Min Range: -0.3866

Max Act: 0.3109. Min Act: -0.0001

Data Index: 844543 (C4 (Web Text))

Max Activating Token Index: 310