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

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

Neuron 5124 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.6103. Min Act: -0.0000

Data Index: 972149 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.5170. Min Act: -0.0000

Data Index: 642864 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.5095. Min Act: -0.0000

Data Index: 1139171 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.5707. Min Act: -0.0000

Data Index: 1128005 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.5288. Min Act: -0.0000

Data Index: 1526474 (Python Code)

Max Activating Token Index: 590

Text #5

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.5457. Min Act: -0.0000

Data Index: 492792 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.4562. Min Act: -0.0000

Data Index: 337278 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.4268. Min Act: -0.0000

Data Index: 1191160 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.4138. Min Act: -0.0000

Data Index: 1395461 (Python Code)

Max Activating Token Index: 692

Text #9

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.4036. Min Act: -0.0000

Data Index: 1100081 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.3100. Min Act: -0.0000

Data Index: 758205 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.4331. Min Act: -0.0000

Data Index: 1366284 (Python Code)

Max Activating Token Index: 783

Text #12

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.4537. Min Act: -0.0000

Data Index: 1337606 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1574902 (Python Code)

Max Activating Token Index: 828

Text #14

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.3264. Min Act: -0.0000

Data Index: 1275759 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.3927. Min Act: -0.0000

Data Index: 1495778 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.3777. Min Act: -0.0000

Data Index: 1471502 (Python Code)

Max Activating Token Index: 820

Text #17

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.3441. Min Act: -0.0000

Data Index: 327110 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.3446. Min Act: -0.0000

Data Index: 844153 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.6103. Min Range: -1.6103

Max Act: 1.2641. Min Act: -0.0000

Data Index: 1368288 (Python Code)

Max Activating Token Index: 678