Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1291 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.4507. Min Act: -0.0001

Data Index: 264577 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.4353. Min Act: -0.0001

Data Index: 316716 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.4261. Min Act: -0.0001

Data Index: 939237 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3826. Min Act: -0.0001

Data Index: 303267 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.4052. Min Act: -0.0001

Data Index: 170198 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3444. Min Act: -0.0001

Data Index: 817294 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3349. Min Act: -0.0001

Data Index: 319752 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2917. Min Act: -0.0001

Data Index: 603615 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3106. Min Act: -0.0001

Data Index: 1000347 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2644. Min Act: -0.0001

Data Index: 1183449 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3038. Min Act: -0.0001

Data Index: 434270 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3106. Min Act: -0.0001

Data Index: 554586 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2984. Min Act: -0.0001

Data Index: 764155 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2970. Min Act: -0.0001

Data Index: 1223727 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2991. Min Act: -0.0001

Data Index: 903692 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2689. Min Act: -0.0001

Data Index: 179897 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2931. Min Act: -0.0001

Data Index: 637527 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2729. Min Act: -0.0001

Data Index: 1293604 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2695. Min Act: -0.0001

Data Index: 867144 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.2772. Min Act: -0.0001

Data Index: 448784 (C4 (Web Text))

Max Activating Token Index: 374