Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 838 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0484. Min Act: -0.0002

Data Index: 95091 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 987448 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0452. Min Act: -0.0002

Data Index: 451337 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0466. Min Act: -0.0002

Data Index: 72136 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0422. Min Act: -0.0002

Data Index: 742375 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0400. Min Act: -0.0002

Data Index: 543591 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0397. Min Act: -0.0002

Data Index: 997730 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0403. Min Act: -0.0002

Data Index: 588454 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0420. Min Act: -0.0002

Data Index: 995375 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0388. Min Act: -0.0002

Data Index: 149024 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1096480 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1186947 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0370. Min Act: -0.0002

Data Index: 514055 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1118110 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0378. Min Act: -0.0002

Data Index: 490044 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0370. Min Act: -0.0002

Data Index: 54927 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0370. Min Act: -0.0002

Data Index: 803417 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0362. Min Act: -0.0002

Data Index: 505577 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0364. Min Act: -0.0002

Data Index: 1244500 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0365. Min Act: -0.0002

Data Index: 72154 (C4 (Web Text))

Max Activating Token Index: 1018