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

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

Neuron 4433 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4082. Min Range: -1.4082

Max Act: 1.4082. Min Act: -0.0000

Data Index: 1364974 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 1.4082. Min Range: -1.4082

Max Act: 1.3670. Min Act: -0.0000

Data Index: 105942 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 1.4082. Min Range: -1.4082

Max Act: 1.0973. Min Act: -0.0000

Data Index: 1611382 (Python Code)

Max Activating Token Index: 374

Text #3

Max Range: 1.4082. Min Range: -1.4082

Max Act: 1.0466. Min Act: -0.0000

Data Index: 524076 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9782. Min Act: 0.0000

Data Index: 1387205 (Python Code)

Max Activating Token Index: 284

Text #5

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9818. Min Act: -0.0000

Data Index: 447017 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 1.4082. Min Range: -1.4082

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1353251 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 1.4082. Min Range: -1.4082

Max Act: 1.0174. Min Act: -0.0000

Data Index: 708662 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1113123 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9754. Min Act: -0.0000

Data Index: 390748 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 1.4082. Min Range: -1.4082

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1269830 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 1.4082. Min Range: -1.4082

Max Act: 1.0613. Min Act: -0.0000

Data Index: 129893 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1445887 (Python Code)

Max Activating Token Index: 934

Text #13

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1460050 (Python Code)

Max Activating Token Index: 789

Text #14

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9726. Min Act: -0.0000

Data Index: 1619058 (Python Code)

Max Activating Token Index: 197

Text #15

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1219439 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9432. Min Act: -0.0000

Data Index: 1271058 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1442480 (Python Code)

Max Activating Token Index: 755

Text #18

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9740. Min Act: -0.0000

Data Index: 427755 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.4082. Min Range: -1.4082

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1538459 (Python Code)

Max Activating Token Index: 150