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

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

Neuron 3652 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: 0.0585. Min Range: -0.0585

Max Act: 0.0585. Min Act: -0.0001

Data Index: 384734 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0548. Min Act: -0.0001

Data Index: 534944 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0496. Min Act: -0.0001

Data Index: 58163 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0516. Min Act: -0.0001

Data Index: 1285084 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1196519 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0442. Min Act: -0.0001

Data Index: 909756 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1214909 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0456. Min Act: -0.0001

Data Index: 305316 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0420. Min Act: -0.0001

Data Index: 538803 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0404. Min Act: -0.0001

Data Index: 392126 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0422. Min Act: -0.0001

Data Index: 36760 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0402. Min Act: -0.0001

Data Index: 1256708 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0398. Min Act: -0.0001

Data Index: 472779 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0414. Min Act: -0.0001

Data Index: 1107301 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0413. Min Act: -0.0001

Data Index: 828916 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0397. Min Act: -0.0001

Data Index: 664650 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0425. Min Act: -0.0001

Data Index: 19552 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0422. Min Act: -0.0001

Data Index: 1143132 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0389. Min Act: -0.0001

Data Index: 430504 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.0585. Min Range: -0.0585

Max Act: 0.0401. Min Act: -0.0001

Data Index: 811331 (C4 (Web Text))

Max Activating Token Index: 31