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

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

Neuron 1694 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4748. Min Range: -2.4748

Max Act: 2.4748. Min Act: -0.0000

Data Index: 120640 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 2.4748. Min Range: -2.4748

Max Act: 2.2883. Min Act: -0.0000

Data Index: 93276 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 2.4748. Min Range: -2.4748

Max Act: 2.2819. Min Act: -0.0000

Data Index: 938414 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.9319. Min Act: -0.0001

Data Index: 292873 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.8853. Min Act: -0.0000

Data Index: 1028499 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.9794. Min Act: -0.0000

Data Index: 836448 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.9822. Min Act: -0.0001

Data Index: 626469 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 2.4748. Min Range: -2.4748

Max Act: 2.2679. Min Act: -0.0000

Data Index: 1157821 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.8177. Min Act: -0.0000

Data Index: 1297167 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.8944. Min Act: -0.0000

Data Index: 818124 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.7824. Min Act: -0.0001

Data Index: 716721 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.7919. Min Act: -0.0000

Data Index: 896855 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.6853. Min Act: -0.0001

Data Index: 24665 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.7541. Min Act: -0.0001

Data Index: 1270059 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.9561. Min Act: -0.0001

Data Index: 825263 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.8549. Min Act: -0.0001

Data Index: 834570 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.8422. Min Act: -0.0001

Data Index: 815745 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.8299. Min Act: -0.0000

Data Index: 172412 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 2.4748. Min Range: -2.4748

Max Act: 2.0525. Min Act: -0.0000

Data Index: 704771 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 2.4748. Min Range: -2.4748

Max Act: 1.8240. Min Act: -0.0001

Data Index: 844274 (C4 (Web Text))

Max Activating Token Index: 897