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

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

Neuron 1033 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4337. Min Range: -6.4337

Max Act: 6.4337. Min Act: -0.0000

Data Index: 409915 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 6.4337. Min Range: -6.4337

Max Act: 5.0362. Min Act: -0.0001

Data Index: 1085958 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 6.4337. Min Range: -6.4337

Max Act: 4.9069. Min Act: -0.0001

Data Index: 689505 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 6.4337. Min Range: -6.4337

Max Act: 4.6474. Min Act: -0.0001

Data Index: 1233191 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 6.4337. Min Range: -6.4337

Max Act: 4.4677. Min Act: -0.0001

Data Index: 74538 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 6.4337. Min Range: -6.4337

Max Act: 4.5445. Min Act: -0.0001

Data Index: 997852 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 6.4337. Min Range: -6.4337

Max Act: 4.0394. Min Act: -0.0001

Data Index: 486102 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 6.4337. Min Range: -6.4337

Max Act: 4.4641. Min Act: -0.0001

Data Index: 309834 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 6.4337. Min Range: -6.4337

Max Act: 4.2580. Min Act: -0.0000

Data Index: 379723 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 6.4337. Min Range: -6.4337

Max Act: 4.2087. Min Act: -0.0001

Data Index: 1090529 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 6.4337. Min Range: -6.4337

Max Act: 4.0157. Min Act: -0.0001

Data Index: 869437 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 6.4337. Min Range: -6.4337

Max Act: 3.9723. Min Act: -0.0000

Data Index: 32964 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 6.4337. Min Range: -6.4337

Max Act: 3.9104. Min Act: -0.0001

Data Index: 1133970 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 6.4337. Min Range: -6.4337

Max Act: 3.4679. Min Act: -0.0000

Data Index: 918846 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 6.4337. Min Range: -6.4337

Max Act: 3.7672. Min Act: -0.0001

Data Index: 170569 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 6.4337. Min Range: -6.4337

Max Act: 3.4497. Min Act: -0.0000

Data Index: 86890 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 6.4337. Min Range: -6.4337

Max Act: 3.4187. Min Act: -0.0001

Data Index: 1256138 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 6.4337. Min Range: -6.4337

Max Act: 3.4779. Min Act: -0.0001

Data Index: 966021 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 6.4337. Min Range: -6.4337

Max Act: 3.4507. Min Act: -0.0001

Data Index: 484043 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 6.4337. Min Range: -6.4337

Max Act: 3.4549. Min Act: -0.0000

Data Index: 915188 (C4 (Web Text))

Max Activating Token Index: 960