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

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

Neuron 2 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.7486. Min Act: -0.0001

Data Index: 23866 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.6958. Min Act: -0.0002

Data Index: 1294843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.6969. Min Act: -0.0002

Data Index: 1070921 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.6573. Min Act: -0.0002

Data Index: 706522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.6139. Min Act: -0.0002

Data Index: 783287 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5464. Min Act: -0.0001

Data Index: 785790 (C4 (Web Text))

Max Activating Token Index: 1020

Text #6

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5451. Min Act: -0.0002

Data Index: 762043 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5420. Min Act: -0.0002

Data Index: 1191030 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5110. Min Act: -0.0001

Data Index: 783574 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5586. Min Act: -0.0001

Data Index: 1323827 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5260. Min Act: -0.0001

Data Index: 1268674 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5295. Min Act: -0.0001

Data Index: 1194449 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5119. Min Act: -0.0002

Data Index: 1171544 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.4797. Min Act: -0.0002

Data Index: 924810 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5065. Min Act: -0.0002

Data Index: 1092176 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5047. Min Act: -0.0001

Data Index: 1227743 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.4861. Min Act: -0.0001

Data Index: 56331 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5350. Min Act: -0.0002

Data Index: 373803 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.5358. Min Act: -0.0002

Data Index: 951388 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.7486. Min Range: -0.7486

Max Act: 0.4841. Min Act: -0.0001

Data Index: 734929 (C4 (Web Text))

Max Activating Token Index: 681