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

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

Neuron 5529 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.9194. Min Act: -0.0002

Data Index: 523092 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8864. Min Act: -0.0002

Data Index: 1343250 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8672. Min Act: -0.0002

Data Index: 663334 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8476. Min Act: -0.0002

Data Index: 705662 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8512. Min Act: -0.0002

Data Index: 1339392 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8654. Min Act: -0.0002

Data Index: 1320944 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8320. Min Act: -0.0002

Data Index: 217179 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8444. Min Act: -0.0003

Data Index: 114733 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8680. Min Act: -0.0002

Data Index: 1142730 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8305. Min Act: -0.0002

Data Index: 1398 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8370. Min Act: -0.0002

Data Index: 1308113 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8413. Min Act: -0.0002

Data Index: 976335 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8365. Min Act: -0.0002

Data Index: 1000756 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8267. Min Act: -0.0002

Data Index: 87081 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8309. Min Act: -0.0002

Data Index: 594986 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8144. Min Act: -0.0002

Data Index: 1107717 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8332. Min Act: -0.0002

Data Index: 1215449 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8517. Min Act: -0.0002

Data Index: 450497 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8288. Min Act: -0.0003

Data Index: 789287 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.9194. Min Range: -0.9194

Max Act: 0.8402. Min Act: -0.0002

Data Index: 704959 (C4 (Web Text))

Max Activating Token Index: 538