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

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

Neuron 4671 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4398. Min Act: -0.0001

Data Index: 1145664 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4131. Min Act: -0.0001

Data Index: 1177881 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3911. Min Act: -0.0001

Data Index: 783935 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4053. Min Act: -0.0001

Data Index: 488556 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3397. Min Act: -0.0001

Data Index: 88841 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3749. Min Act: -0.0001

Data Index: 1196172 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3553. Min Act: -0.0001

Data Index: 498959 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3643. Min Act: -0.0001

Data Index: 925560 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3395. Min Act: -0.0001

Data Index: 715518 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3366. Min Act: -0.0001

Data Index: 1257410 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3483. Min Act: -0.0001

Data Index: 1119579 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3480. Min Act: -0.0001

Data Index: 176060 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3516. Min Act: -0.0001

Data Index: 1310218 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3379. Min Act: -0.0001

Data Index: 381249 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3453. Min Act: -0.0001

Data Index: 569083 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3610. Min Act: -0.0001

Data Index: 807121 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3374. Min Act: -0.0001

Data Index: 185214 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3357. Min Act: -0.0001

Data Index: 273480 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3101. Min Act: -0.0001

Data Index: 1161090 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3154. Min Act: -0.0001

Data Index: 1279645 (C4 (Web Text))

Max Activating Token Index: 48