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

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

Neuron 3254 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: 0.2567. Min Range: -0.2567

Max Act: 0.2567. Min Act: -0.0001

Data Index: 169444 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2472. Min Act: -0.0001

Data Index: 203314 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2355. Min Act: -0.0001

Data Index: 441547 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2331. Min Act: -0.0001

Data Index: 27062 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2074. Min Act: -0.0001

Data Index: 944995 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2126. Min Act: -0.0001

Data Index: 726414 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2108. Min Act: -0.0001

Data Index: 814467 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2047. Min Act: -0.0001

Data Index: 778724 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2042. Min Act: -0.0001

Data Index: 168677 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1226241 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1984. Min Act: -0.0001

Data Index: 421477 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2037. Min Act: -0.0001

Data Index: 1165293 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2103. Min Act: -0.0001

Data Index: 618223 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1971. Min Act: -0.0001

Data Index: 209673 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1052388 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.2013. Min Act: -0.0001

Data Index: 742984 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1992. Min Act: -0.0001

Data Index: 122386 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1246709 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1991. Min Act: -0.0001

Data Index: 292282 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.2567. Min Range: -0.2567

Max Act: 0.1999. Min Act: -0.0001

Data Index: 1079579 (C4 (Web Text))

Max Activating Token Index: 395