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

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

Neuron 4012 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.3694. Min Act: -0.0000

Data Index: 748921 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1093302 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1536998 (Python Code)

Max Activating Token Index: 727

Text #3

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2540. Min Act: -0.0000

Data Index: 970434 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2432. Min Act: -0.0000

Data Index: 715852 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1638316 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1586498 (Python Code)

Max Activating Token Index: 390

Text #7

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2394. Min Act: -0.0000

Data Index: 136453 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1542978 (Python Code)

Max Activating Token Index: 457

Text #9

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2334. Min Act: -0.0000

Data Index: 985994 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1525709 (Python Code)

Max Activating Token Index: 1016

Text #11

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2313. Min Act: -0.0000

Data Index: 92505 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1426090 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1493292 (Python Code)

Max Activating Token Index: 514

Text #14

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1651740 (Python Code)

Max Activating Token Index: 24

Text #15

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1113344 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1651259 (Python Code)

Max Activating Token Index: 438

Text #17

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1633654 (Python Code)

Max Activating Token Index: 342

Text #18

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1603012 (Python Code)

Max Activating Token Index: 1003

Text #19

Max Range: 0.3694. Min Range: -0.3694

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1524127 (Python Code)

Max Activating Token Index: 390