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

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

Neuron 3790 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.4092. Min Act: -0.0000

Data Index: 29850 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3968. Min Act: -0.0001

Data Index: 1117613 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1087807 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3537. Min Act: -0.0001

Data Index: 813093 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.4057. Min Act: -0.0001

Data Index: 715756 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3510. Min Act: -0.0001

Data Index: 848735 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3531. Min Act: -0.0001

Data Index: 401383 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1035017 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3644. Min Act: -0.0000

Data Index: 664309 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3340. Min Act: -0.0000

Data Index: 886701 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3384. Min Act: -0.0000

Data Index: 717166 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3439. Min Act: -0.0001

Data Index: 1239143 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3498. Min Act: -0.0000

Data Index: 593342 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3718. Min Act: -0.0000

Data Index: 903282 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3608. Min Act: -0.0001

Data Index: 833674 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3521. Min Act: -0.0001

Data Index: 1187271 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.4081. Min Act: -0.0000

Data Index: 741814 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3558. Min Act: -0.0001

Data Index: 1629 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3275. Min Act: -0.0000

Data Index: 321002 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.4092. Min Range: -0.4092

Max Act: 0.3237. Min Act: -0.0001

Data Index: 173119 (C4 (Web Text))

Max Activating Token Index: 496