Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 127 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2407. Min Act: -0.0003

Data Index: 75524 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2226. Min Act: -0.0003

Data Index: 715424 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2245. Min Act: -0.0003

Data Index: 1213902 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1961. Min Act: -0.0003

Data Index: 233113 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2024. Min Act: -0.0003

Data Index: 695377 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2005. Min Act: -0.0003

Data Index: 722438 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2068. Min Act: -0.0003

Data Index: 240804 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2124. Min Act: -0.0003

Data Index: 1019832 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2001. Min Act: -0.0003

Data Index: 1200257 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1956. Min Act: -0.0003

Data Index: 822862 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1933. Min Act: -0.0003

Data Index: 1067877 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1922. Min Act: -0.0003

Data Index: 864135 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1924. Min Act: -0.0003

Data Index: 1292642 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1883. Min Act: -0.0003

Data Index: 230688 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1816. Min Act: -0.0003

Data Index: 526199 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1914. Min Act: -0.0003

Data Index: 839217 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1758. Min Act: -0.0003

Data Index: 3298 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1897. Min Act: -0.0003

Data Index: 127625 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1755. Min Act: -0.0003

Data Index: 219695 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1884. Min Act: -0.0003

Data Index: 583229 (C4 (Web Text))

Max Activating Token Index: 258