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

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

Neuron 3640 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: 3.7561. Min Range: -3.7561

Max Act: 3.7561. Min Act: -0.0001

Data Index: 53080 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.3045. Min Act: -0.0001

Data Index: 1300270 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.4164. Min Act: -0.0001

Data Index: 155954 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.2140. Min Act: -0.0001

Data Index: 1167959 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.5812. Min Act: -0.0001

Data Index: 1260322 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.1154. Min Act: -0.0001

Data Index: 897644 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.0838. Min Act: -0.0001

Data Index: 58006 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.2131. Min Act: -0.0001

Data Index: 208308 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.6360. Min Act: -0.0001

Data Index: 241284 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.7770. Min Act: -0.0001

Data Index: 603396 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.0157. Min Act: -0.0001

Data Index: 313857 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.9946. Min Act: -0.0001

Data Index: 1197859 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.0742. Min Act: -0.0001

Data Index: 439945 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 3.7561. Min Range: -3.7561

Max Act: 3.0684. Min Act: -0.0001

Data Index: 1162553 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.8975. Min Act: -0.0001

Data Index: 537784 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.8857. Min Act: -0.0001

Data Index: 595792 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.8509. Min Act: -0.0001

Data Index: 1342499 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.5623. Min Act: -0.0001

Data Index: 241826 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.9814. Min Act: -0.0001

Data Index: 193545 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 3.7561. Min Range: -3.7561

Max Act: 2.8268. Min Act: -0.0001

Data Index: 21254 (C4 (Web Text))

Max Activating Token Index: 710