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

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

Neuron 3909 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5150. Min Act: -0.0002

Data Index: 576669 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5188. Min Act: -0.0002

Data Index: 1096876 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4999. Min Act: -0.0002

Data Index: 1325077 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5073. Min Act: -0.0002

Data Index: 147985 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5063. Min Act: -0.0002

Data Index: 807390 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5405. Min Act: -0.0002

Data Index: 297930 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4974. Min Act: -0.0002

Data Index: 771344 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5192. Min Act: -0.0002

Data Index: 998186 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5126. Min Act: -0.0002

Data Index: 1181851 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.5282. Min Act: -0.0002

Data Index: 526602 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4935. Min Act: -0.0002

Data Index: 234567 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4989. Min Act: -0.0002

Data Index: 489648 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4984. Min Act: -0.0002

Data Index: 911212 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4614. Min Act: -0.0002

Data Index: 766216 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4735. Min Act: -0.0002

Data Index: 297611 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4796. Min Act: -0.0002

Data Index: 1236593 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4737. Min Act: -0.0002

Data Index: 437108 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4717. Min Act: -0.0002

Data Index: 974804 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4580. Min Act: -0.0002

Data Index: 66661 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.5405. Min Range: -0.5405

Max Act: 0.4864. Min Act: -0.0002

Data Index: 1136190 (C4 (Web Text))

Max Activating Token Index: 278