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

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

Neuron 3364 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.8042. Min Act: -0.0001

Data Index: 860780 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.8168. Min Act: -0.0001

Data Index: 1342981 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.5982. Min Act: -0.0001

Data Index: 451121 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.5230. Min Act: -0.0001

Data Index: 763153 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.5535. Min Act: -0.0001

Data Index: 89195 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.5772. Min Act: -0.0001

Data Index: 1352055 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.5075. Min Act: -0.0001

Data Index: 141817 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.5091. Min Act: -0.0001

Data Index: 378456 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.5251. Min Act: -0.0001

Data Index: 1104493 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.4658. Min Act: -0.0001

Data Index: 434837 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.4252. Min Act: -0.0001

Data Index: 761554 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.4409. Min Act: -0.0001

Data Index: 952387 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.3687. Min Act: -0.0001

Data Index: 272634 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.3371. Min Act: -0.0001

Data Index: 582366 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.3650. Min Act: -0.0001

Data Index: 963374 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.3488. Min Act: -0.0001

Data Index: 1145264 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.2229. Min Act: -0.0001

Data Index: 1013790 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.2922. Min Act: -0.0001

Data Index: 939174 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.2917. Min Act: -0.0001

Data Index: 1104250 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 1.8168. Min Range: -1.8168

Max Act: 1.2818. Min Act: -0.0001

Data Index: 848080 (C4 (Web Text))

Max Activating Token Index: 897