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

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

Neuron 4752 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: 0.8492. Min Range: -0.8492

Max Act: 0.8492. Min Act: -0.0000

Data Index: 611245 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1159918 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.7305. Min Act: -0.0000

Data Index: 1118186 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.7563. Min Act: -0.0000

Data Index: 595408 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1275042 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.6347. Min Act: -0.0000

Data Index: 970141 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1342320 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1116776 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.6094. Min Act: 0.0001

Data Index: 1293283 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.6088. Min Act: -0.0000

Data Index: 796968 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.5891. Min Act: -0.0000

Data Index: 132386 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.5190. Min Act: -0.0000

Data Index: 259531 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1137503 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.5520. Min Act: -0.0000

Data Index: 38899 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.5833. Min Act: -0.0000

Data Index: 91136 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.5236. Min Act: -0.0000

Data Index: 56598 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.5534. Min Act: -0.0000

Data Index: 331750 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.5398. Min Act: -0.0000

Data Index: 1062638 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.5428. Min Act: -0.0000

Data Index: 708334 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.8492. Min Range: -0.8492

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1254438 (C4 (Web Text))

Max Activating Token Index: 779