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

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

Neuron 3025 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.9948. Min Act: -0.0001

Data Index: 1061484 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.7567. Min Act: -0.0001

Data Index: 1079829 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.6276. Min Act: -0.0001

Data Index: 286342 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.6836. Min Act: -0.0001

Data Index: 79490 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.6131. Min Act: -0.0001

Data Index: 72759 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.6277. Min Act: -0.0001

Data Index: 1122555 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.5032. Min Act: -0.0001

Data Index: 199642 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.4431. Min Act: -0.0001

Data Index: 440222 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.5721. Min Act: -0.0001

Data Index: 51208 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.6638. Min Act: -0.0001

Data Index: 376808 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.4978. Min Act: -0.0001

Data Index: 1309146 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.4793. Min Act: -0.0001

Data Index: 741925 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.4722. Min Act: -0.0001

Data Index: 1054317 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.5277. Min Act: -0.0001

Data Index: 883957 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.5147. Min Act: -0.0001

Data Index: 261000 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.5078. Min Act: -0.0001

Data Index: 1028645 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.4343. Min Act: -0.0001

Data Index: 372655 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.4454. Min Act: -0.0001

Data Index: 1212402 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.4377. Min Act: -0.0001

Data Index: 739694 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 1.9948. Min Range: -1.9948

Max Act: 1.4239. Min Act: -0.0001

Data Index: 439977 (C4 (Web Text))

Max Activating Token Index: 760