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

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

Neuron 274 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8771. Min Range: -2.8771

Max Act: 2.8771. Min Act: -0.0000

Data Index: 1122181 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 2.8771. Min Range: -2.8771

Max Act: 2.6190. Min Act: -0.0000

Data Index: 1142768 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 2.8771. Min Range: -2.8771

Max Act: 2.4844. Min Act: -0.0000

Data Index: 62236 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 2.8771. Min Range: -2.8771

Max Act: 2.0849. Min Act: -0.0000

Data Index: 787452 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.9811. Min Act: -0.0000

Data Index: 948981 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.9466. Min Act: -0.0000

Data Index: 375244 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.8119. Min Act: -0.0000

Data Index: 1108502 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.7221. Min Act: -0.0000

Data Index: 1245944 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 2.8771. Min Range: -2.8771

Max Act: 2.0643. Min Act: -0.0001

Data Index: 388053 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.9001. Min Act: -0.0000

Data Index: 903902 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 2.8771. Min Range: -2.8771

Max Act: 2.1110. Min Act: -0.0000

Data Index: 258786 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.8709. Min Act: -0.0000

Data Index: 562603 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.7157. Min Act: -0.0000

Data Index: 692609 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.7218. Min Act: -0.0000

Data Index: 822277 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.7911. Min Act: -0.0000

Data Index: 443287 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.5847. Min Act: -0.0000

Data Index: 1327584 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.6587. Min Act: -0.0000

Data Index: 871861 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.7451. Min Act: -0.0000

Data Index: 1161092 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.8737. Min Act: -0.0001

Data Index: 1331998 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 2.8771. Min Range: -2.8771

Max Act: 1.6479. Min Act: -0.0000

Data Index: 916251 (C4 (Web Text))

Max Activating Token Index: 628