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

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

Neuron 1018 in Layer 0

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: 0.6093. Min Range: -0.6093

Max Act: 0.6093. Min Act: -0.0001

Data Index: 1010116 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.5640. Min Act: -0.0001

Data Index: 1341239 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.5578. Min Act: -0.0001

Data Index: 258475 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.5601. Min Act: -0.0001

Data Index: 1079209 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.5284. Min Act: -0.0001

Data Index: 168439 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.5213. Min Act: -0.0001

Data Index: 73652 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.5070. Min Act: -0.0001

Data Index: 703605 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.5056. Min Act: -0.0001

Data Index: 1168199 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.4950. Min Act: -0.0001

Data Index: 987063 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.4953. Min Act: -0.0001

Data Index: 418323 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.5026. Min Act: -0.0001

Data Index: 1187175 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.4827. Min Act: -0.0002

Data Index: 920971 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.4891. Min Act: -0.0001

Data Index: 520823 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.4889. Min Act: -0.0001

Data Index: 310126 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.4846. Min Act: -0.0001

Data Index: 872180 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.4743. Min Act: -0.0001

Data Index: 498984 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.4724. Min Act: -0.0001

Data Index: 947670 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.4734. Min Act: -0.0001

Data Index: 422257 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.4807. Min Act: -0.0001

Data Index: 682638 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.6093. Min Range: -0.6093

Max Act: 0.4764. Min Act: -0.0001

Data Index: 95202 (C4 (Web Text))

Max Activating Token Index: 131