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

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

Neuron 3990 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4612. Min Act: -0.0000

Data Index: 725766 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4342. Min Act: -0.0000

Data Index: 601649 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4190. Min Act: -0.0000

Data Index: 875919 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1080580 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.4014. Min Act: 0.0001

Data Index: 281985 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3750. Min Act: -0.0000

Data Index: 45421 (C4 (Web Text))

Max Activating Token Index: 422

Text #6

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3514. Min Act: -0.0000

Data Index: 382090 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1138873 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3424. Min Act: -0.0000

Data Index: 631305 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1168398 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3371. Min Act: 0.0001

Data Index: 1035596 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3289. Min Act: 0.0001

Data Index: 34371 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3284. Min Act: -0.0000

Data Index: 923515 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3131. Min Act: -0.0000

Data Index: 287211 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3320. Min Act: -0.0000

Data Index: 488553 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3133. Min Act: 0.0001

Data Index: 1063481 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3089. Min Act: -0.0000

Data Index: 719661 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1097392 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.3001. Min Act: 0.0001

Data Index: 370150 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.4612. Min Range: -0.4612

Max Act: 0.2968. Min Act: -0.0000

Data Index: 1131646 (C4 (Web Text))

Max Activating Token Index: 346