Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 157 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.9946. Min Act: -0.0001

Data Index: 894459 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 1.0046. Min Range: -1.0046

Max Act: 1.0046. Min Act: -0.0001

Data Index: 18499 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7952. Min Act: -0.0001

Data Index: 7860 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.9201. Min Act: -0.0001

Data Index: 121898 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8974. Min Act: -0.0001

Data Index: 140266 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8345. Min Act: -0.0001

Data Index: 1208523 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.9095. Min Act: -0.0001

Data Index: 154965 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8704. Min Act: -0.0001

Data Index: 1028270 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8650. Min Act: -0.0001

Data Index: 610142 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8068. Min Act: -0.0001

Data Index: 909919 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7838. Min Act: -0.0001

Data Index: 1042516 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8213. Min Act: -0.0001

Data Index: 968316 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8282. Min Act: -0.0001

Data Index: 206126 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8840. Min Act: -0.0001

Data Index: 1218675 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8217. Min Act: -0.0001

Data Index: 526084 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7987. Min Act: -0.0001

Data Index: 100855 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8320. Min Act: -0.0001

Data Index: 182125 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7888. Min Act: -0.0001

Data Index: 1058759 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.8356. Min Act: -0.0001

Data Index: 1342058 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 1.0046. Min Range: -1.0046

Max Act: 0.7165. Min Act: -0.0001

Data Index: 297504 (C4 (Web Text))

Max Activating Token Index: 902