Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 703 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.7167. Min Range: -4.7167

Max Act: 4.7167. Min Act: -0.0000

Data Index: 1043311 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 4.7167. Min Range: -4.7167

Max Act: 4.0502. Min Act: -0.0000

Data Index: 922658 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.8385. Min Act: -0.0000

Data Index: 302205 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.5288. Min Act: -0.0000

Data Index: 376099 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.4440. Min Act: -0.0000

Data Index: 1029335 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.4313. Min Act: -0.0000

Data Index: 948508 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.3931. Min Act: -0.0000

Data Index: 285563 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.3954. Min Act: -0.0000

Data Index: 1100709 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.2031. Min Act: -0.0000

Data Index: 62627 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.3107. Min Act: -0.0000

Data Index: 350573 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.1452. Min Act: -0.0000

Data Index: 684312 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.2975. Min Act: -0.0000

Data Index: 56493 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.3607. Min Act: -0.0000

Data Index: 131218 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.2040. Min Act: -0.0000

Data Index: 937438 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 4.7167. Min Range: -4.7167

Max Act: 2.8893. Min Act: 0.0000

Data Index: 1270699 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.1054. Min Act: -0.0000

Data Index: 66825 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.2380. Min Act: -0.0000

Data Index: 24026 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 4.7167. Min Range: -4.7167

Max Act: 3.0409. Min Act: -0.0000

Data Index: 677892 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 4.7167. Min Range: -4.7167

Max Act: 2.9807. Min Act: -0.0000

Data Index: 661792 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 4.7167. Min Range: -4.7167

Max Act: 2.9812. Min Act: -0.0000

Data Index: 1006857 (C4 (Web Text))

Max Activating Token Index: 119