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

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

Neuron 3294 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: 1.7750. Min Range: -1.7750

Max Act: 1.7750. Min Act: -0.0001

Data Index: 1027432 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.5078. Min Act: -0.0001

Data Index: 1113367 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.6309. Min Act: -0.0001

Data Index: 33124 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4855. Min Act: -0.0001

Data Index: 141925 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.5519. Min Act: -0.0001

Data Index: 882841 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.6315. Min Act: -0.0001

Data Index: 233378 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.6750. Min Act: -0.0001

Data Index: 1126929 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.6135. Min Act: -0.0001

Data Index: 776636 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.5781. Min Act: -0.0001

Data Index: 1112529 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4430. Min Act: -0.0001

Data Index: 1158500 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.5906. Min Act: -0.0001

Data Index: 345776 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.5110. Min Act: -0.0001

Data Index: 537066 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4739. Min Act: -0.0001

Data Index: 732067 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.3931. Min Act: -0.0001

Data Index: 1206354 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.5548. Min Act: -0.0001

Data Index: 936102 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4583. Min Act: -0.0001

Data Index: 748321 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.5466. Min Act: -0.0000

Data Index: 297131 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.5150. Min Act: -0.0000

Data Index: 383479 (C4 (Web Text))

Max Activating Token Index: 797

Text #18

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4351. Min Act: -0.0001

Data Index: 407625 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 1.7750. Min Range: -1.7750

Max Act: 1.4697. Min Act: -0.0001

Data Index: 1104837 (C4 (Web Text))

Max Activating Token Index: 732