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

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

Neuron 1472 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.7108. Min Act: -0.0000

Data Index: 155195 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.4987. Min Act: -0.0000

Data Index: 332248 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.1773. Min Act: -0.0000

Data Index: 1136957 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.2468. Min Act: -0.0000

Data Index: 757609 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.9424. Min Act: -0.0000

Data Index: 509989 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 2.7108. Min Range: -2.7108

Max Act: 2.0244. Min Act: -0.0000

Data Index: 1143181 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.9054. Min Act: -0.0000

Data Index: 72638 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.9589. Min Act: -0.0000

Data Index: 95944 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.9473. Min Act: -0.0000

Data Index: 36292 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.9348. Min Act: -0.0000

Data Index: 401908 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.9099. Min Act: -0.0000

Data Index: 387837 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.8950. Min Act: -0.0000

Data Index: 572374 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.8684. Min Act: -0.0000

Data Index: 550821 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.8409. Min Act: -0.0000

Data Index: 104708 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.7973. Min Act: -0.0000

Data Index: 441969 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.7926. Min Act: -0.0000

Data Index: 504890 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.7656. Min Act: -0.0000

Data Index: 209101 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.8476. Min Act: -0.0000

Data Index: 427663 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.7420. Min Act: -0.0000

Data Index: 53506 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 2.7108. Min Range: -2.7108

Max Act: 1.7075. Min Act: -0.0000

Data Index: 799616 (C4 (Web Text))

Max Activating Token Index: 160