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

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

Neuron 454 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.1471. Min Act: -0.0001

Data Index: 1214092 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0945. Min Act: -0.0001

Data Index: 1021613 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.1144. Min Act: -0.0001

Data Index: 412543 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.1471. Min Range: -1.1471

Max Act: 1.0239. Min Act: -0.0001

Data Index: 1332492 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9702. Min Act: -0.0001

Data Index: 202818 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9679. Min Act: -0.0001

Data Index: 721741 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9615. Min Act: -0.0001

Data Index: 821420 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9513. Min Act: -0.0001

Data Index: 756344 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9208. Min Act: -0.0001

Data Index: 1305589 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9463. Min Act: -0.0001

Data Index: 819369 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9322. Min Act: -0.0001

Data Index: 808387 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9271. Min Act: -0.0001

Data Index: 1208791 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9213. Min Act: -0.0001

Data Index: 294787 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9129. Min Act: -0.0001

Data Index: 372634 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8893. Min Act: -0.0001

Data Index: 199125 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.9258. Min Act: -0.0001

Data Index: 1071750 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8852. Min Act: -0.0001

Data Index: 540744 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8378. Min Act: -0.0001

Data Index: 527604 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8891. Min Act: -0.0001

Data Index: 1137928 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 1.1471. Min Range: -1.1471

Max Act: 0.8814. Min Act: -0.0001

Data Index: 319077 (C4 (Web Text))

Max Activating Token Index: 274