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

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

Neuron 3571 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.7830. Min Act: -0.0000

Data Index: 1096759 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6324. Min Act: -0.0000

Data Index: 479944 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1054719 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6229. Min Act: -0.0000

Data Index: 831008 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.6214. Min Act: 0.0000

Data Index: 147865 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1124910 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5789. Min Act: -0.0000

Data Index: 830134 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5341. Min Act: 0.0000

Data Index: 431015 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5333. Min Act: 0.0001

Data Index: 538720 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5285. Min Act: -0.0000

Data Index: 366061 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5372. Min Act: -0.0000

Data Index: 824737 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5230. Min Act: 0.0000

Data Index: 728593 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1155650 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.5015. Min Act: -0.0000

Data Index: 17081 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4997. Min Act: 0.0001

Data Index: 652223 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1146217 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4741. Min Act: -0.0000

Data Index: 494400 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4450. Min Act: -0.0000

Data Index: 835109 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4436. Min Act: -0.0000

Data Index: 214161 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.7830. Min Range: -0.7830

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1122550 (C4 (Web Text))

Max Activating Token Index: 922