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

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

Neuron 1114 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.4350. Min Act: -0.0000

Data Index: 484407 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.3071. Min Act: -0.0000

Data Index: 1335861 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.2418. Min Act: -0.0000

Data Index: 697279 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.2142. Min Act: -0.0000

Data Index: 631318 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.2108. Min Act: -0.0000

Data Index: 187995 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.2168. Min Act: -0.0000

Data Index: 121749 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.1908. Min Act: -0.0000

Data Index: 321050 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.1577. Min Act: -0.0000

Data Index: 518785 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.1289. Min Act: -0.0000

Data Index: 529724 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.0276. Min Act: -0.0000

Data Index: 1226329 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.0219. Min Act: -0.0000

Data Index: 208148 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.0537. Min Act: -0.0000

Data Index: 356021 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.0841. Min Act: -0.0000

Data Index: 836667 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.0261. Min Act: -0.0000

Data Index: 704605 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 2.4350. Min Range: -2.4350

Max Act: 1.9481. Min Act: -0.0000

Data Index: 557457 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.0426. Min Act: -0.0000

Data Index: 281364 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.0369. Min Act: -0.0000

Data Index: 925314 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 2.4350. Min Range: -2.4350

Max Act: 1.8557. Min Act: -0.0000

Data Index: 795369 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 2.4350. Min Range: -2.4350

Max Act: 2.0120. Min Act: -0.0000

Data Index: 340085 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 2.4350. Min Range: -2.4350

Max Act: 1.8811. Min Act: -0.0000

Data Index: 872036 (C4 (Web Text))

Max Activating Token Index: 57