Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3694 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 480905 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0484. Min Act: -0.0003

Data Index: 541910 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0464. Min Act: -0.0002

Data Index: 471210 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0448. Min Act: -0.0002

Data Index: 452939 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0457. Min Act: -0.0002

Data Index: 322165 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0440. Min Act: -0.0003

Data Index: 983914 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0445. Min Act: -0.0003

Data Index: 70944 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0428. Min Act: -0.0003

Data Index: 983335 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0423. Min Act: -0.0003

Data Index: 178687 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0418. Min Act: -0.0003

Data Index: 370683 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0402. Min Act: -0.0003

Data Index: 775479 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0420. Min Act: -0.0002

Data Index: 255012 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0410. Min Act: -0.0002

Data Index: 488899 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1098100 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0396. Min Act: -0.0003

Data Index: 232147 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1013116 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0402. Min Act: -0.0003

Data Index: 94388 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0399. Min Act: -0.0003

Data Index: 75974 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0404. Min Act: -0.0003

Data Index: 743225 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0411. Min Act: -0.0003

Data Index: 868204 (C4 (Web Text))

Max Activating Token Index: 91