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

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

Neuron 2685 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5356. Min Range: -1.5356

Max Act: 1.5356. Min Act: -0.0001

Data Index: 434240 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.5356. Min Range: -1.5356

Max Act: 1.0940. Min Act: -0.0000

Data Index: 714462 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 1.5356. Min Range: -1.5356

Max Act: 1.1259. Min Act: -0.0000

Data Index: 331898 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 1.5356. Min Range: -1.5356

Max Act: 1.1066. Min Act: -0.0001

Data Index: 172152 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 1.5356. Min Range: -1.5356

Max Act: 1.0374. Min Act: -0.0001

Data Index: 127718 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.9855. Min Act: -0.0001

Data Index: 525951 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.9892. Min Act: -0.0000

Data Index: 950462 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.9774. Min Act: -0.0001

Data Index: 822046 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.8366. Min Act: -0.0001

Data Index: 118913 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.9047. Min Act: -0.0001

Data Index: 71532 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.9488. Min Act: -0.0001

Data Index: 589888 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.8969. Min Act: -0.0000

Data Index: 219814 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.8998. Min Act: -0.0001

Data Index: 254318 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.9337. Min Act: -0.0001

Data Index: 1259007 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.9342. Min Act: -0.0000

Data Index: 40006 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.9402. Min Act: -0.0001

Data Index: 473417 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.9363. Min Act: -0.0001

Data Index: 856694 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.8898. Min Act: -0.0001

Data Index: 663032 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.8935. Min Act: -0.0001

Data Index: 427458 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 1.5356. Min Range: -1.5356

Max Act: 0.8916. Min Act: -0.0001

Data Index: 142881 (C4 (Web Text))

Max Activating Token Index: 853