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

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

Neuron 3807 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: 3.6113. Min Range: -3.6113

Max Act: 3.6113. Min Act: -0.0001

Data Index: 1204185 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 3.6113. Min Range: -3.6113

Max Act: 3.2776. Min Act: -0.0001

Data Index: 466893 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 3.6113. Min Range: -3.6113

Max Act: 3.2339. Min Act: -0.0001

Data Index: 1147326 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 3.6113. Min Range: -3.6113

Max Act: 3.4707. Min Act: -0.0001

Data Index: 468587 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 3.6113. Min Range: -3.6113

Max Act: 3.0893. Min Act: -0.0001

Data Index: 727169 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 3.6113. Min Range: -3.6113

Max Act: 3.2384. Min Act: -0.0001

Data Index: 856664 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 3.6113. Min Range: -3.6113

Max Act: 3.2335. Min Act: -0.0001

Data Index: 918548 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 3.6113. Min Range: -3.6113

Max Act: 3.1253. Min Act: -0.0001

Data Index: 1090478 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.9582. Min Act: -0.0001

Data Index: 419569 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.9359. Min Act: -0.0001

Data Index: 991725 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.9335. Min Act: -0.0001

Data Index: 571023 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.8870. Min Act: -0.0001

Data Index: 1326619 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.5227. Min Act: -0.0001

Data Index: 423699 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.4916. Min Act: -0.0001

Data Index: 388326 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.5916. Min Act: -0.0001

Data Index: 155888 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.4975. Min Act: -0.0001

Data Index: 370506 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.3826. Min Act: -0.0001

Data Index: 37607 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.0951. Min Act: -0.0001

Data Index: 1262800 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.1672. Min Act: -0.0001

Data Index: 958805 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 3.6113. Min Range: -3.6113

Max Act: 2.4178. Min Act: -0.0001

Data Index: 494643 (C4 (Web Text))

Max Activating Token Index: 827