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

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

Neuron 1301 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: 3.0162. Min Range: -3.0162

Max Act: 2.8987. Min Act: -0.0001

Data Index: 354619 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 3.0162. Min Range: -3.0162

Max Act: 3.0162. Min Act: -0.0001

Data Index: 366599 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.6961. Min Act: -0.0001

Data Index: 651634 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.6062. Min Act: -0.0001

Data Index: 793627 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.3100. Min Act: -0.0001

Data Index: 930609 (C4 (Web Text))

Max Activating Token Index: 654

Text #5

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.3983. Min Act: -0.0001

Data Index: 814231 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.2659. Min Act: -0.0001

Data Index: 310980 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.1456. Min Act: -0.0001

Data Index: 1244515 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.3643. Min Act: -0.0001

Data Index: 709651 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.2133. Min Act: -0.0001

Data Index: 551409 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.3284. Min Act: -0.0001

Data Index: 198377 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.3169. Min Act: -0.0001

Data Index: 1340800 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.4000. Min Act: -0.0001

Data Index: 889496 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 3.0162. Min Range: -3.0162

Max Act: 1.9817. Min Act: -0.0001

Data Index: 544938 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.2888. Min Act: -0.0001

Data Index: 1207507 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 3.0162. Min Range: -3.0162

Max Act: 1.9332. Min Act: -0.0001

Data Index: 921060 (C4 (Web Text))

Max Activating Token Index: 1001

Text #16

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.0553. Min Act: -0.0001

Data Index: 39679 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.1499. Min Act: -0.0001

Data Index: 455366 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.2753. Min Act: -0.0001

Data Index: 1083985 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 3.0162. Min Range: -3.0162

Max Act: 2.0892. Min Act: -0.0001

Data Index: 504356 (C4 (Web Text))

Max Activating Token Index: 518