Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 287 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.9934. Min Range: -2.9934

Max Act: 2.9934. Min Act: -0.0000

Data Index: 548740 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 2.9934. Min Range: -2.9934

Max Act: 2.6786. Min Act: -0.0000

Data Index: 497664 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.7966. Min Act: -0.0000

Data Index: 203983 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.8853. Min Act: -0.0001

Data Index: 57949 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.6509. Min Act: -0.0000

Data Index: 97858 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.7980. Min Act: -0.0000

Data Index: 429465 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.6708. Min Act: -0.0000

Data Index: 184496 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.6974. Min Act: -0.0000

Data Index: 998950 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.6335. Min Act: -0.0000

Data Index: 570728 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.6216. Min Act: -0.0000

Data Index: 435586 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.5295. Min Act: -0.0000

Data Index: 688769 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.4202. Min Act: -0.0000

Data Index: 1160403 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.5255. Min Act: -0.0000

Data Index: 675666 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.4382. Min Act: -0.0000

Data Index: 390562 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.4356. Min Act: -0.0000

Data Index: 43188 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.4467. Min Act: -0.0000

Data Index: 258296 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.3943. Min Act: -0.0000

Data Index: 1304729 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.3708. Min Act: -0.0000

Data Index: 352077 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.3241. Min Act: -0.0000

Data Index: 949621 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 2.9934. Min Range: -2.9934

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1153804 (C4 (Web Text))

Max Activating Token Index: 391