Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1740 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4231. Min Range: -4.4231

Max Act: 4.1747. Min Act: -0.0000

Data Index: 1094044 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 4.4231. Min Range: -4.4231

Max Act: 4.4231. Min Act: -0.0000

Data Index: 268142 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.8996. Min Act: -0.0000

Data Index: 367239 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.7241. Min Act: -0.0000

Data Index: 260784 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.4286. Min Act: -0.0000

Data Index: 109988 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.3149. Min Act: -0.0000

Data Index: 548798 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.2806. Min Act: -0.0000

Data Index: 390266 (C4 (Web Text))

Max Activating Token Index: 718

Text #7

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.0961. Min Act: -0.0000

Data Index: 60181 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.1349. Min Act: -0.0000

Data Index: 267827 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.2934. Min Act: -0.0000

Data Index: 1061876 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.0885. Min Act: -0.0000

Data Index: 24040 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.2450. Min Act: -0.0000

Data Index: 93919 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.2162. Min Act: -0.0000

Data Index: 1076796 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 4.4231. Min Range: -4.4231

Max Act: 2.9910. Min Act: -0.0000

Data Index: 524876 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.1235. Min Act: -0.0000

Data Index: 836149 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 4.4231. Min Range: -4.4231

Max Act: 3.0440. Min Act: -0.0000

Data Index: 1258470 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 4.4231. Min Range: -4.4231

Max Act: 2.9489. Min Act: -0.0000

Data Index: 420743 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 4.4231. Min Range: -4.4231

Max Act: 2.9060. Min Act: -0.0000

Data Index: 1091257 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 4.4231. Min Range: -4.4231

Max Act: 2.8614. Min Act: -0.0000

Data Index: 287053 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 4.4231. Min Range: -4.4231

Max Act: 2.8368. Min Act: -0.0000

Data Index: 834956 (C4 (Web Text))

Max Activating Token Index: 73