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

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

Neuron 6058 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.0973. Min Range: -1.0973

Max Act: 1.0742. Min Act: -0.0001

Data Index: 1305673 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 1.0973. Min Range: -1.0973

Max Act: 1.0973. Min Act: -0.0001

Data Index: 933739 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.0973. Min Range: -1.0973

Max Act: 1.0424. Min Act: -0.0001

Data Index: 376543 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.0973. Min Range: -1.0973

Max Act: 1.0227. Min Act: -0.0001

Data Index: 358537 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 1.0973. Min Range: -1.0973

Max Act: 1.0085. Min Act: -0.0001

Data Index: 556783 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 1.0973. Min Range: -1.0973

Max Act: 1.0280. Min Act: -0.0001

Data Index: 366372 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 1.0973. Min Range: -1.0973

Max Act: 1.0038. Min Act: -0.0001

Data Index: 408629 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 1.0973. Min Range: -1.0973

Max Act: 1.0253. Min Act: -0.0001

Data Index: 521942 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9889. Min Act: -0.0001

Data Index: 31546 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9982. Min Act: -0.0001

Data Index: 653682 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9907. Min Act: -0.0001

Data Index: 1040904 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9666. Min Act: -0.0001

Data Index: 944638 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9709. Min Act: -0.0001

Data Index: 683587 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9796. Min Act: -0.0001

Data Index: 406528 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9680. Min Act: -0.0001

Data Index: 1296513 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9544. Min Act: -0.0001

Data Index: 629748 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9626. Min Act: -0.0001

Data Index: 1272871 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9850. Min Act: -0.0001

Data Index: 1219747 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9856. Min Act: -0.0001

Data Index: 452880 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 1.0973. Min Range: -1.0973

Max Act: 0.9635. Min Act: -0.0001

Data Index: 277482 (C4 (Web Text))

Max Activating Token Index: 474