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

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

Neuron 78 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: 5.0650. Min Range: -5.0650

Max Act: 4.7455. Min Act: -0.0000

Data Index: 958382 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 5.0650. Min Range: -5.0650

Max Act: 5.0650. Min Act: -0.0001

Data Index: 546356 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.3196. Min Act: -0.0000

Data Index: 795211 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.3730. Min Act: -0.0000

Data Index: 270305 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 5.0650. Min Range: -5.0650

Max Act: 3.7623. Min Act: -0.0001

Data Index: 926483 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.2918. Min Act: -0.0000

Data Index: 1114429 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.5003. Min Act: -0.0000

Data Index: 364677 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.3298. Min Act: -0.0000

Data Index: 1199037 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 5.0650. Min Range: -5.0650

Max Act: 3.9874. Min Act: -0.0000

Data Index: 374218 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.4776. Min Act: -0.0000

Data Index: 308546 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.3041. Min Act: -0.0000

Data Index: 241699 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 5.0650. Min Range: -5.0650

Max Act: 3.7712. Min Act: -0.0001

Data Index: 853056 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.0687. Min Act: -0.0001

Data Index: 114014 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.5752. Min Act: -0.0000

Data Index: 1293277 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.0452. Min Act: -0.0000

Data Index: 809661 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 5.0650. Min Range: -5.0650

Max Act: 3.8547. Min Act: -0.0000

Data Index: 911442 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.0022. Min Act: -0.0000

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.2974. Min Act: -0.0000

Data Index: 414181 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 5.0650. Min Range: -5.0650

Max Act: 4.2228. Min Act: -0.0000

Data Index: 122635 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 5.0650. Min Range: -5.0650

Max Act: 3.8614. Min Act: -0.0000

Data Index: 140102 (C4 (Web Text))

Max Activating Token Index: 294