Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5506 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.3352. Min Act: -0.0001

Data Index: 250626 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2881. Min Act: -0.0001

Data Index: 947969 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2806. Min Act: -0.0000

Data Index: 977278 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2767. Min Act: -0.0001

Data Index: 508724 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2844. Min Act: -0.0001

Data Index: 1280389 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2962. Min Act: -0.0001

Data Index: 994806 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2635. Min Act: -0.0001

Data Index: 300071 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2443. Min Act: -0.0000

Data Index: 838439 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2306. Min Act: -0.0001

Data Index: 28068 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2409. Min Act: -0.0001

Data Index: 501984 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2291. Min Act: -0.0001

Data Index: 637977 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2402. Min Act: -0.0001

Data Index: 108266 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2257. Min Act: -0.0001

Data Index: 430227 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2455. Min Act: -0.0001

Data Index: 999856 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2215. Min Act: -0.0001

Data Index: 954828 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2013. Min Act: -0.0001

Data Index: 165966 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.1924. Min Act: -0.0001

Data Index: 1034993 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2020. Min Act: -0.0001

Data Index: 1221138 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2366. Min Act: -0.0001

Data Index: 753305 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.3352. Min Range: -0.3352

Max Act: 0.2014. Min Act: -0.0001

Data Index: 6538 (C4 (Web Text))

Max Activating Token Index: 180