Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4549 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1466. Min Act: -0.0000

Data Index: 873112 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1505. Min Act: -0.0000

Data Index: 196114 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1328. Min Act: -0.0000

Data Index: 30469 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1327. Min Act: -0.0000

Data Index: 574969 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1236. Min Act: -0.0000

Data Index: 213791 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1185. Min Act: -0.0000

Data Index: 293262 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1070700 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1105. Min Act: -0.0000

Data Index: 395478 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1286771 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1114. Min Act: -0.0000

Data Index: 1137042 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1064. Min Act: -0.0000

Data Index: 338602 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1570277 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1012578 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0979. Min Act: -0.0000

Data Index: 441675 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.1045. Min Act: -0.0000

Data Index: 375519 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1021842 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1300009 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0953. Min Act: -0.0000

Data Index: 664561 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0953. Min Act: -0.0000

Data Index: 753350 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.1505. Min Range: -0.1505

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1335573 (C4 (Web Text))

Max Activating Token Index: 198