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

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

Neuron 1666 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: 0.6484. Min Range: -0.6484

Max Act: 0.6484. Min Act: -0.0001

Data Index: 485313 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.5784. Min Act: -0.0001

Data Index: 581595 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.5480. Min Act: -0.0001

Data Index: 471713 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.5661. Min Act: -0.0001

Data Index: 34930 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.5090. Min Act: -0.0001

Data Index: 614028 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.5042. Min Act: -0.0001

Data Index: 1215244 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4798. Min Act: -0.0001

Data Index: 618316 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4951. Min Act: -0.0001

Data Index: 222965 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4920. Min Act: -0.0001

Data Index: 395875 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4913. Min Act: -0.0001

Data Index: 781569 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4909. Min Act: -0.0001

Data Index: 1099747 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4886. Min Act: -0.0001

Data Index: 591625 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4705. Min Act: -0.0001

Data Index: 780272 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4829. Min Act: -0.0001

Data Index: 940211 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4743. Min Act: -0.0001

Data Index: 587317 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4946. Min Act: -0.0001

Data Index: 1212138 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4710. Min Act: -0.0001

Data Index: 1183866 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4674. Min Act: -0.0001

Data Index: 1088761 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4681. Min Act: -0.0001

Data Index: 1240354 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.6484. Min Range: -0.6484

Max Act: 0.4652. Min Act: -0.0001

Data Index: 384587 (C4 (Web Text))

Max Activating Token Index: 1001