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

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

Neuron 735 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.9064. Min Act: -0.0001

Data Index: 1534137 (Python Code)

Max Activating Token Index: 926

Text #1

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6651. Min Act: -0.0001

Data Index: 1576898 (Python Code)

Max Activating Token Index: 291

Text #2

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6194. Min Act: -0.0001

Data Index: 1495133 (Python Code)

Max Activating Token Index: 641

Text #3

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6128. Min Act: -0.0000

Data Index: 975688 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6119. Min Act: -0.0001

Data Index: 1550839 (Python Code)

Max Activating Token Index: 330

Text #5

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5977. Min Act: -0.0001

Data Index: 1484361 (Python Code)

Max Activating Token Index: 303

Text #6

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5984. Min Act: -0.0001

Data Index: 1423645 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5577. Min Act: -0.0001

Data Index: 1505152 (Python Code)

Max Activating Token Index: 715

Text #8

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5685. Min Act: -0.0001

Data Index: 1575171 (Python Code)

Max Activating Token Index: 577

Text #9

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5486. Min Act: -0.0001

Data Index: 1655923 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5243. Min Act: -0.0001

Data Index: 1467132 (Python Code)

Max Activating Token Index: 347

Text #11

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1464366 (Python Code)

Max Activating Token Index: 551

Text #12

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5541. Min Act: -0.0001

Data Index: 1595436 (Python Code)

Max Activating Token Index: 349

Text #13

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.4846. Min Act: -0.0001

Data Index: 1411349 (Python Code)

Max Activating Token Index: 344

Text #14

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.4995. Min Act: -0.0001

Data Index: 1509331 (Python Code)

Max Activating Token Index: 870

Text #15

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5621. Min Act: -0.0001

Data Index: 1422362 (Python Code)

Max Activating Token Index: 566

Text #16

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5109. Min Act: -0.0001

Data Index: 1407719 (Python Code)

Max Activating Token Index: 729

Text #17

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5258. Min Act: -0.0000

Data Index: 433030 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5008. Min Act: -0.0001

Data Index: 1565126 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.4991. Min Act: -0.0001

Data Index: 1073157 (C4 (Web Text))

Max Activating Token Index: 433