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

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

Neuron 485 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: 0.9411. Min Range: -0.9411

Max Act: 0.9411. Min Act: -0.0002

Data Index: 1135148 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8922. Min Act: -0.0002

Data Index: 461148 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8924. Min Act: -0.0002

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8576. Min Act: -0.0002

Data Index: 101386 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8557. Min Act: -0.0002

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8481. Min Act: -0.0002

Data Index: 642988 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8606. Min Act: -0.0002

Data Index: 1123909 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8275. Min Act: -0.0002

Data Index: 1237496 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8333. Min Act: -0.0002

Data Index: 693850 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8350. Min Act: -0.0002

Data Index: 816503 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8314. Min Act: -0.0002

Data Index: 731583 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8104. Min Act: -0.0002

Data Index: 371664 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7927. Min Act: -0.0002

Data Index: 972252 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7980. Min Act: -0.0002

Data Index: 376774 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8060. Min Act: -0.0002

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7952. Min Act: -0.0002

Data Index: 231983 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8099. Min Act: -0.0002

Data Index: 255373 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7914. Min Act: -0.0002

Data Index: 980819 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7962. Min Act: -0.0002

Data Index: 85720 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7795. Min Act: -0.0002

Data Index: 1221820 (C4 (Web Text))

Max Activating Token Index: 327