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

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

Neuron 240 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2244. Min Range: -4.2244

Max Act: 4.2244. Min Act: -0.0000

Data Index: 1038378 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 4.2244. Min Range: -4.2244

Max Act: 3.2080. Min Act: -0.0000

Data Index: 486058 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 4.2244. Min Range: -4.2244

Max Act: 3.2089. Min Act: -0.0000

Data Index: 848368 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 4.2244. Min Range: -4.2244

Max Act: 3.1690. Min Act: -0.0000

Data Index: 1316068 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.9339. Min Act: -0.0000

Data Index: 340478 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.9805. Min Act: -0.0000

Data Index: 362638 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.7067. Min Act: -0.0000

Data Index: 1193693 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.7884. Min Act: -0.0000

Data Index: 63094 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.6902. Min Act: -0.0000

Data Index: 625942 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.4582. Min Act: -0.0000

Data Index: 546248 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.5452. Min Act: -0.0000

Data Index: 562996 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.5493. Min Act: -0.0000

Data Index: 1334083 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.5133. Min Act: -0.0000

Data Index: 380061 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.4916. Min Act: -0.0000

Data Index: 348011 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.4882. Min Act: -0.0000

Data Index: 1182330 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.3012. Min Act: -0.0000

Data Index: 167284 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.3830. Min Act: -0.0000

Data Index: 989531 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.3341. Min Act: -0.0000

Data Index: 807682 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.3175. Min Act: -0.0000

Data Index: 414386 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 4.2244. Min Range: -4.2244

Max Act: 2.2794. Min Act: -0.0000

Data Index: 12869 (C4 (Web Text))

Max Activating Token Index: 139