Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 935 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0021. Min Range: -1.0021

Max Act: 1.0021. Min Act: -0.0001

Data Index: 143479 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.8195. Min Act: -0.0001

Data Index: 663700 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.8050. Min Act: -0.0001

Data Index: 223015 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7946. Min Act: -0.0001

Data Index: 262700 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7811. Min Act: -0.0001

Data Index: 43147 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7510. Min Act: -0.0001

Data Index: 1031077 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7494. Min Act: -0.0001

Data Index: 566395 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7968. Min Act: -0.0001

Data Index: 1145277 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7675. Min Act: -0.0001

Data Index: 806230 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7410. Min Act: -0.0001

Data Index: 1333094 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.7356. Min Act: -0.0001

Data Index: 1071284 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6992. Min Act: -0.0001

Data Index: 172213 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6994. Min Act: -0.0001

Data Index: 201121 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6835. Min Act: -0.0001

Data Index: 712249 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6654. Min Act: -0.0001

Data Index: 451920 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6414. Min Act: -0.0001

Data Index: 317719 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6667. Min Act: -0.0001

Data Index: 441467 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6270. Min Act: -0.0001

Data Index: 888440 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6223. Min Act: -0.0001

Data Index: 15927 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 1.0021. Min Range: -1.0021

Max Act: 0.6210. Min Act: -0.0001

Data Index: 1296411 (C4 (Web Text))

Max Activating Token Index: 151