Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3649 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.1199. Min Act: -0.0001

Data Index: 486317 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.1186. Min Act: -0.0000

Data Index: 453972 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.2088. Min Act: -0.0001

Data Index: 842234 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0980. Min Act: -0.0000

Data Index: 168693 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0607. Min Act: -0.0001

Data Index: 275604 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 1.2088. Min Range: -1.2088

Max Act: 1.0007. Min Act: -0.0000

Data Index: 174458 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9936. Min Act: -0.0000

Data Index: 294890 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9254. Min Act: -0.0001

Data Index: 623792 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9366. Min Act: -0.0000

Data Index: 227353 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8861. Min Act: -0.0001

Data Index: 1100937 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9274. Min Act: -0.0001

Data Index: 1004940 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8832. Min Act: -0.0000

Data Index: 221113 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1104566 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8464. Min Act: -0.0000

Data Index: 790717 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8533. Min Act: -0.0001

Data Index: 1140301 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8078. Min Act: -0.0001

Data Index: 131982 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8777. Min Act: -0.0000

Data Index: 60946 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8370. Min Act: -0.0001

Data Index: 804460 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9034. Min Act: -0.0001

Data Index: 523034 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8203. Min Act: -0.0001

Data Index: 652948 (C4 (Web Text))

Max Activating Token Index: 686