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

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

Neuron 1974 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5005. Min Range: -4.5005

Max Act: 4.5005. Min Act: -0.0000

Data Index: 933428 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 4.5005. Min Range: -4.5005

Max Act: 4.3285. Min Act: -0.0000

Data Index: 399663 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.9004. Min Act: -0.0000

Data Index: 504529 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.7021. Min Act: -0.0000

Data Index: 416560 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.4384. Min Act: -0.0000

Data Index: 232701 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.5788. Min Act: -0.0000

Data Index: 512723 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.2393. Min Act: -0.0000

Data Index: 106973 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.4161. Min Act: -0.0000

Data Index: 797951 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.0864. Min Act: -0.0000

Data Index: 24666 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.2097. Min Act: -0.0000

Data Index: 1234598 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.3467. Min Act: -0.0000

Data Index: 1270052 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.0456. Min Act: -0.0000

Data Index: 1091064 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.2992. Min Act: -0.0000

Data Index: 562495 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 4.5005. Min Range: -4.5005

Max Act: 3.0444. Min Act: -0.0000

Data Index: 1135280 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 4.5005. Min Range: -4.5005

Max Act: 2.8395. Min Act: -0.0000

Data Index: 115761 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 4.5005. Min Range: -4.5005

Max Act: 2.9345. Min Act: -0.0000

Data Index: 375842 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 4.5005. Min Range: -4.5005

Max Act: 2.7471. Min Act: -0.0000

Data Index: 1161690 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 4.5005. Min Range: -4.5005

Max Act: 2.8592. Min Act: -0.0000

Data Index: 140409 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 4.5005. Min Range: -4.5005

Max Act: 2.8394. Min Act: -0.0000

Data Index: 198410 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 4.5005. Min Range: -4.5005

Max Act: 2.8094. Min Act: -0.0000

Data Index: 1235357 (C4 (Web Text))

Max Activating Token Index: 427