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

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

Neuron 1640 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: 0.6309. Min Range: -0.6309

Max Act: 0.6309. Min Act: -0.0000

Data Index: 728169 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.5769. Min Act: -0.0000

Data Index: 212573 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4874. Min Act: -0.0001

Data Index: 877604 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4831. Min Act: -0.0000

Data Index: 759678 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.4325. Min Act: -0.0000

Data Index: 753713 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3816. Min Act: -0.0000

Data Index: 19315 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3848. Min Act: -0.0000

Data Index: 1328762 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3832. Min Act: -0.0000

Data Index: 846835 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3810. Min Act: -0.0000

Data Index: 1105491 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3783. Min Act: -0.0000

Data Index: 201491 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3886. Min Act: -0.0001

Data Index: 1037531 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3726. Min Act: -0.0000

Data Index: 777900 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3446. Min Act: -0.0000

Data Index: 383596 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1036558 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3515. Min Act: -0.0000

Data Index: 882500 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3322. Min Act: -0.0001

Data Index: 84258 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3339. Min Act: 0.0000

Data Index: 1222957 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3238. Min Act: -0.0000

Data Index: 71312 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3151. Min Act: -0.0000

Data Index: 418169 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.6309. Min Range: -0.6309

Max Act: 0.3155. Min Act: -0.0000

Data Index: 67575 (C4 (Web Text))

Max Activating Token Index: 405