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

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

Neuron 2421 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: 1.7750. Min Range: -1.7750

Max Act: 1.7750. Min Act: -0.0001

Data Index: 1014119 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.6251. Min Act: -0.0001

Data Index: 216086 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.5124. Min Act: -0.0001

Data Index: 1061467 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4954. Min Act: -0.0001

Data Index: 409088 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4606. Min Act: -0.0001

Data Index: 899882 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4826. Min Act: -0.0001

Data Index: 718910 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4941. Min Act: -0.0001

Data Index: 1282260 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.5156. Min Act: -0.0001

Data Index: 748510 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.3995. Min Act: -0.0001

Data Index: 410513 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4933. Min Act: -0.0001

Data Index: 1179786 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.3785. Min Act: -0.0001

Data Index: 1240127 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.3755. Min Act: -0.0001

Data Index: 921048 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.3529. Min Act: -0.0001

Data Index: 263837 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.3875. Min Act: -0.0001

Data Index: 68078 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.3134. Min Act: -0.0001

Data Index: 952953 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4161. Min Act: -0.0001

Data Index: 886204 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.3457. Min Act: -0.0001

Data Index: 116745 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.3681. Min Act: -0.0001

Data Index: 1336524 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.3297. Min Act: -0.0001

Data Index: 557840 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.3916. Min Act: -0.0001

Data Index: 1217536 (C4 (Web Text))

Max Activating Token Index: 836