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

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

Neuron 3687 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.5305. Min Act: -0.0000

Data Index: 1311349 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4788. Min Act: -0.0000

Data Index: 236397 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4621. Min Act: -0.0000

Data Index: 896156 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1043682 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4596. Min Act: -0.0000

Data Index: 696399 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1344723 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1634954 (Python Code)

Max Activating Token Index: 860

Text #7

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1334718 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4323. Min Act: -0.0000

Data Index: 255198 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4151. Min Act: -0.0000

Data Index: 447 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4183. Min Act: -0.0000

Data Index: 560840 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4289. Min Act: -0.0000

Data Index: 969028 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4065. Min Act: -0.0000

Data Index: 1471577 (Python Code)

Max Activating Token Index: 343

Text #13

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1223012 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4191. Min Act: -0.0000

Data Index: 461132 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.3880. Min Act: -0.0000

Data Index: 209746 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4178. Min Act: -0.0000

Data Index: 644061 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.3948. Min Act: -0.0000

Data Index: 498514 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.4252. Min Act: -0.0000

Data Index: 488678 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.5305. Min Range: -0.5305

Max Act: 0.3902. Min Act: -0.0000

Data Index: 355087 (C4 (Web Text))

Max Activating Token Index: 683