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

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

Neuron 2776 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1946. Min Range: -1.1946

Max Act: 1.1946. Min Act: -0.0000

Data Index: 351421 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 1.1946. Min Range: -1.1946

Max Act: 1.1274. Min Act: -0.0000

Data Index: 943828 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 1.1946. Min Range: -1.1946

Max Act: 1.0399. Min Act: 0.0000

Data Index: 1111957 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.9699. Min Act: -0.0000

Data Index: 562731 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.8885. Min Act: -0.0000

Data Index: 227443 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1052746 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7962. Min Act: -0.0000

Data Index: 440206 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7865. Min Act: -0.0000

Data Index: 805641 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7780. Min Act: -0.0000

Data Index: 184731 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7685. Min Act: -0.0000

Data Index: 602703 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7603. Min Act: -0.0000

Data Index: 349235 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7681. Min Act: -0.0000

Data Index: 86455 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1324469 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7535. Min Act: -0.0000

Data Index: 126256 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7099. Min Act: -0.0000

Data Index: 940156 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7647. Min Act: -0.0000

Data Index: 709156 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7093. Min Act: 0.0000

Data Index: 630730 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1011081 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7220. Min Act: -0.0000

Data Index: 1340470 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.1946. Min Range: -1.1946

Max Act: 0.7038. Min Act: -0.0000

Data Index: 842605 (C4 (Web Text))

Max Activating Token Index: 297