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

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

Neuron 4376 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3212. Min Range: -1.3212

Max Act: 1.3212. Min Act: -0.0003

Data Index: 879510 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 1.3212. Min Range: -1.3212

Max Act: 1.3212. Min Act: -0.0003

Data Index: 128185 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 1.3212. Min Range: -1.3212

Max Act: 1.3212. Min Act: -0.0002

Data Index: 491936 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9826. Min Act: -0.0002

Data Index: 21199 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9770. Min Act: -0.0002

Data Index: 601912 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9337. Min Act: -0.0002

Data Index: 468404 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9505. Min Act: -0.0002

Data Index: 230912 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9201. Min Act: -0.0002

Data Index: 783591 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9414. Min Act: -0.0002

Data Index: 684940 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9216. Min Act: -0.0002

Data Index: 1114682 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9082. Min Act: -0.0002

Data Index: 17003 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9090. Min Act: -0.0002

Data Index: 1069838 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9042. Min Act: -0.0003

Data Index: 1208132 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.8861. Min Act: -0.0002

Data Index: 150055 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.8983. Min Act: -0.0002

Data Index: 820357 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.8981. Min Act: -0.0002

Data Index: 121950 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9064. Min Act: -0.0002

Data Index: 271468 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9064. Min Act: -0.0002

Data Index: 1284306 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9064. Min Act: -0.0002

Data Index: 296186 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 1.3212. Min Range: -1.3212

Max Act: 0.9064. Min Act: -0.0002

Data Index: 204862 (C4 (Web Text))

Max Activating Token Index: 3