Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3567 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.5562. Min Act: -0.0001

Data Index: 1226726 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4107. Min Act: -0.0001

Data Index: 1403341 (Python Code)

Max Activating Token Index: 752

Text #2

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.4468. Min Act: -0.0001

Data Index: 1419917 (Python Code)

Max Activating Token Index: 705

Text #3

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3995. Min Act: -0.0000

Data Index: 251401 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1363977 (Python Code)

Max Activating Token Index: 989

Text #5

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3885. Min Act: 0.0000

Data Index: 953514 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1039629 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3694. Min Act: -0.0000

Data Index: 593827 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1160586 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3664. Min Act: -0.0001

Data Index: 255036 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3644. Min Act: -0.0000

Data Index: 1204215 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3585. Min Act: -0.0000

Data Index: 559078 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3552. Min Act: -0.0000

Data Index: 33470 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3551. Min Act: -0.0000

Data Index: 914092 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3418. Min Act: -0.0001

Data Index: 231990 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3547. Min Act: -0.0001

Data Index: 1416149 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3387. Min Act: -0.0000

Data Index: 898155 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1231642 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3516. Min Act: -0.0001

Data Index: 897653 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.5562. Min Range: -0.5562

Max Act: 0.3592. Min Act: -0.0001

Data Index: 1435466 (Python Code)

Max Activating Token Index: 655