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

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

Neuron 3888 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.5477. Min Act: -0.0001

Data Index: 581684 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.5264. Min Act: -0.0001

Data Index: 160520 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.5003. Min Act: -0.0001

Data Index: 199675 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4934. Min Act: -0.0001

Data Index: 26101 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4330. Min Act: -0.0001

Data Index: 470757 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4074. Min Act: -0.0001

Data Index: 1172839 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4489. Min Act: -0.0001

Data Index: 507109 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4647. Min Act: -0.0001

Data Index: 499269 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4776. Min Act: -0.0001

Data Index: 311709 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4327. Min Act: -0.0001

Data Index: 159266 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3781. Min Act: -0.0001

Data Index: 296838 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4097. Min Act: -0.0001

Data Index: 868062 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4188. Min Act: -0.0001

Data Index: 1084975 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3938. Min Act: -0.0001

Data Index: 1088188 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.4285. Min Act: -0.0001

Data Index: 186271 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3851. Min Act: -0.0001

Data Index: 891145 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3791. Min Act: -0.0001

Data Index: 1069597 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3259. Min Act: -0.0001

Data Index: 363210 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3996. Min Act: -0.0001

Data Index: 1136396 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.5477. Min Range: -0.5477

Max Act: 0.3867. Min Act: -0.0001

Data Index: 1261066 (C4 (Web Text))

Max Activating Token Index: 177