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

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

Neuron 3523 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: 1.8963. Min Range: -1.8963

Max Act: 1.8963. Min Act: -0.0001

Data Index: 867849 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.7600. Min Act: -0.0001

Data Index: 465128 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.7938. Min Act: -0.0001

Data Index: 478172 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.6089. Min Act: -0.0001

Data Index: 1317816 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.5805. Min Act: -0.0001

Data Index: 1330085 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.6215. Min Act: -0.0001

Data Index: 966600 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.5674. Min Act: -0.0001

Data Index: 1178359 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.4354. Min Act: -0.0001

Data Index: 1144266 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.4064. Min Act: -0.0001

Data Index: 1337799 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.4453. Min Act: -0.0001

Data Index: 1043585 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.5446. Min Act: -0.0000

Data Index: 1201019 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.5182. Min Act: -0.0001

Data Index: 377851 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.4125. Min Act: -0.0001

Data Index: 209466 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.4385. Min Act: -0.0001

Data Index: 161212 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.4746. Min Act: -0.0001

Data Index: 173574 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.3914. Min Act: -0.0001

Data Index: 151446 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.4675. Min Act: -0.0000

Data Index: 637811 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.4367. Min Act: -0.0001

Data Index: 59023 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.2795. Min Act: -0.0001

Data Index: 1233576 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 1.8963. Min Range: -1.8963

Max Act: 1.2687. Min Act: -0.0001

Data Index: 936476 (C4 (Web Text))

Max Activating Token Index: 357