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

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

Neuron 477 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0880. Min Act: -0.0001

Data Index: 903057 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1335742 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1152078 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0550. Min Act: -0.0001

Data Index: 769278 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0519. Min Act: -0.0001

Data Index: 330537 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0443. Min Act: -0.0001

Data Index: 188453 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0555. Min Act: -0.0001

Data Index: 902529 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0489. Min Act: -0.0001

Data Index: 427305 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0500. Min Act: -0.0001

Data Index: 511450 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0279. Min Act: -0.0001

Data Index: 328924 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0483. Min Act: -0.0001

Data Index: 292594 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0480. Min Act: -0.0001

Data Index: 500456 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0516. Min Act: -0.0001

Data Index: 14001 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1266869 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0531. Min Act: -0.0001

Data Index: 911339 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1329577 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0487. Min Act: -0.0001

Data Index: 422404 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0577. Min Act: -0.0001

Data Index: 29560 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0426. Min Act: -0.0001

Data Index: 23162 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.0880. Min Range: -0.0880

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1170237 (C4 (Web Text))

Max Activating Token Index: 350