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

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

Neuron 1783 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0432. Min Act: -0.0001

Data Index: 947601 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0402. Min Act: -0.0001

Data Index: 641716 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0321. Min Act: -0.0001

Data Index: 337832 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1302225 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0305. Min Act: -0.0001

Data Index: 3922 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0301. Min Act: -0.0001

Data Index: 555068 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0300. Min Act: -0.0001

Data Index: 654043 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1231719 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0298. Min Act: -0.0001

Data Index: 926709 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0300. Min Act: -0.0001

Data Index: 159780 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1126251 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0293. Min Act: -0.0001

Data Index: 836376 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0307. Min Act: -0.0001

Data Index: 477459 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0272. Min Act: -0.0001

Data Index: 134644 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0294. Min Act: -0.0001

Data Index: 258189 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0269. Min Act: -0.0001

Data Index: 59600 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0285. Min Act: -0.0001

Data Index: 410048 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0277. Min Act: -0.0001

Data Index: 870095 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1035603 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0266. Min Act: -0.0001

Data Index: 46817 (C4 (Web Text))

Max Activating Token Index: 993