Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3921 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7683. Min Act: -0.0001

Data Index: 1221309 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7436. Min Act: -0.0001

Data Index: 353905 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6538. Min Act: -0.0000

Data Index: 694031 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7461. Min Act: -0.0001

Data Index: 1151081 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7337. Min Act: -0.0001

Data Index: 639354 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6712. Min Act: -0.0001

Data Index: 154794 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6907. Min Act: -0.0001

Data Index: 327817 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6368. Min Act: -0.0001

Data Index: 992582 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5909. Min Act: -0.0000

Data Index: 314839 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6473. Min Act: -0.0001

Data Index: 574051 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5618. Min Act: -0.0001

Data Index: 955584 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6188. Min Act: -0.0001

Data Index: 1084392 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5635. Min Act: -0.0001

Data Index: 391096 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6594. Min Act: -0.0001

Data Index: 72050 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6632. Min Act: -0.0001

Data Index: 187904 (C4 (Web Text))

Max Activating Token Index: 693

Text #15

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5758. Min Act: -0.0000

Data Index: 793264 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7288. Min Act: -0.0001

Data Index: 1014577 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6136. Min Act: -0.0001

Data Index: 272489 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6326. Min Act: -0.0001

Data Index: 340906 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6356. Min Act: -0.0000

Data Index: 860992 (C4 (Web Text))

Max Activating Token Index: 24