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

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

Neuron 5086 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: 0.5954. Min Range: -0.5954

Max Act: 0.5954. Min Act: -0.0002

Data Index: 509152 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5333. Min Act: -0.0002

Data Index: 728076 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5389. Min Act: -0.0002

Data Index: 1207330 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5357. Min Act: -0.0002

Data Index: 449630 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5255. Min Act: -0.0003

Data Index: 973513 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5265. Min Act: -0.0002

Data Index: 966615 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5006. Min Act: -0.0002

Data Index: 153966 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4953. Min Act: -0.0002

Data Index: 303621 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4982. Min Act: -0.0002

Data Index: 13543 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4966. Min Act: -0.0002

Data Index: 1112338 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4864. Min Act: -0.0002

Data Index: 427771 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4903. Min Act: -0.0002

Data Index: 80827 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5030. Min Act: -0.0002

Data Index: 320411 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4750. Min Act: -0.0002

Data Index: 522693 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4848. Min Act: -0.0002

Data Index: 271731 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4855. Min Act: -0.0002

Data Index: 264181 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4956. Min Act: -0.0002

Data Index: 248202 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4702. Min Act: -0.0002

Data Index: 279387 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4709. Min Act: -0.0002

Data Index: 352428 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4697. Min Act: -0.0002

Data Index: 1157174 (C4 (Web Text))

Max Activating Token Index: 381