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

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

Neuron 5551 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.3514. Min Act: -0.0002

Data Index: 1310944 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.3602. Min Act: -0.0001

Data Index: 662292 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.3359. Min Act: -0.0001

Data Index: 1010565 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.3364. Min Act: -0.0001

Data Index: 725172 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.3521. Min Act: -0.0001

Data Index: 633028 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2862. Min Act: -0.0001

Data Index: 1102114 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2587. Min Act: -0.0001

Data Index: 471897 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.3285. Min Act: -0.0001

Data Index: 876674 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2526. Min Act: -0.0001

Data Index: 979997 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2555. Min Act: -0.0001

Data Index: 320075 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2552. Min Act: -0.0001

Data Index: 1336510 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2344. Min Act: -0.0001

Data Index: 369689 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2331. Min Act: -0.0001

Data Index: 1226265 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2266. Min Act: -0.0001

Data Index: 33504 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2163. Min Act: -0.0001

Data Index: 721991 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2172. Min Act: -0.0001

Data Index: 779107 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2084. Min Act: -0.0001

Data Index: 92363 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2428. Min Act: -0.0001

Data Index: 74593 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2149. Min Act: -0.0001

Data Index: 635062 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.3602. Min Range: -0.3602

Max Act: 0.2039. Min Act: -0.0001

Data Index: 1229723 (C4 (Web Text))

Max Activating Token Index: 686