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

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

Neuron 4614 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: 2.3288. Min Range: -2.3288

Max Act: 2.3288. Min Act: 0.0000

Data Index: 728855 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 2.3288. Min Range: -2.3288

Max Act: 2.1702. Min Act: -0.0000

Data Index: 270501 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 2.3288. Min Range: -2.3288

Max Act: 2.1089. Min Act: -0.0000

Data Index: 57290 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 2.3288. Min Range: -2.3288

Max Act: 2.0051. Min Act: -0.0000

Data Index: 664036 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.8291. Min Act: -0.0000

Data Index: 1044827 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.7297. Min Act: -0.0000

Data Index: 1280635 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.9243. Min Act: -0.0000

Data Index: 1046815 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.8562. Min Act: -0.0000

Data Index: 982992 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.7363. Min Act: -0.0000

Data Index: 230576 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.7204. Min Act: -0.0000

Data Index: 1191417 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.7137. Min Act: -0.0000

Data Index: 1100798 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.5359. Min Act: -0.0000

Data Index: 1190096 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.4674. Min Act: -0.0000

Data Index: 1396515 (Python Code)

Max Activating Token Index: 268

Text #13

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.5964. Min Act: -0.0000

Data Index: 556382 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.5900. Min Act: -0.0000

Data Index: 84447 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.5596. Min Act: -0.0000

Data Index: 1121778 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.3848. Min Act: -0.0000

Data Index: 110619 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.5631. Min Act: -0.0000

Data Index: 1258938 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.5465. Min Act: -0.0000

Data Index: 413046 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 2.3288. Min Range: -2.3288

Max Act: 1.5392. Min Act: -0.0000

Data Index: 24795 (C4 (Web Text))

Max Activating Token Index: 553