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

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

Neuron 318 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.9717. Min Act: -0.0000

Data Index: 766775 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.2041. Min Act: -0.0000

Data Index: 840734 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.0060. Min Act: -0.0000

Data Index: 1262951 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.0791. Min Act: -0.0000

Data Index: 793158 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.9717. Min Range: -1.9717

Max Act: 1.0194. Min Act: -0.0000

Data Index: 89830 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1218723 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.9039. Min Act: -0.0000

Data Index: 300112 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.8591. Min Act: -0.0000

Data Index: 645958 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.8541. Min Act: -0.0000

Data Index: 18257 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.8559. Min Act: -0.0000

Data Index: 366318 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.7774. Min Act: -0.0000

Data Index: 19009 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.8487. Min Act: -0.0000

Data Index: 392798 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.7839. Min Act: -0.0000

Data Index: 369423 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.7416. Min Act: -0.0000

Data Index: 969478 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.7324. Min Act: -0.0000

Data Index: 325715 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1276046 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1150395 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1004228 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.7392. Min Act: -0.0000

Data Index: 46976 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 1.9717. Min Range: -1.9717

Max Act: 0.6658. Min Act: -0.0000

Data Index: 1026170 (C4 (Web Text))

Max Activating Token Index: 789