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

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

Neuron 2664 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0491. Min Act: -0.0001

Data Index: 1084072 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1095120 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0427. Min Act: -0.0001

Data Index: 846200 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0447. Min Act: -0.0001

Data Index: 1333597 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0421. Min Act: -0.0001

Data Index: 584507 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1209487 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1640565 (Python Code)

Max Activating Token Index: 832

Text #7

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0421. Min Act: -0.0001

Data Index: 776466 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1256860 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0394. Min Act: -0.0001

Data Index: 1104178 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0416. Min Act: -0.0001

Data Index: 898288 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0400. Min Act: -0.0001

Data Index: 988201 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0417. Min Act: -0.0001

Data Index: 709968 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1628860 (Python Code)

Max Activating Token Index: 556

Text #14

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0401. Min Act: -0.0001

Data Index: 1485963 (Python Code)

Max Activating Token Index: 168

Text #15

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0414. Min Act: -0.0002

Data Index: 581484 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0426. Min Act: -0.0002

Data Index: 129042 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0394. Min Act: -0.0001

Data Index: 724847 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1602672 (Python Code)

Max Activating Token Index: 375

Text #19

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0408. Min Act: -0.0001

Data Index: 431658 (C4 (Web Text))

Max Activating Token Index: 725