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

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

Neuron 1861 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: 1.6951. Min Range: -1.6951

Max Act: 1.6951. Min Act: -0.0001

Data Index: 591990 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5824. Min Act: -0.0001

Data Index: 1084110 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.5470. Min Act: -0.0001

Data Index: 852511 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.4669. Min Act: -0.0001

Data Index: 1297757 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3842. Min Act: -0.0001

Data Index: 557927 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3359. Min Act: -0.0001

Data Index: 1159688 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3238. Min Act: -0.0001

Data Index: 528497 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.3100. Min Act: -0.0001

Data Index: 1046692 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.2572. Min Act: -0.0001

Data Index: 266685 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.2162. Min Act: -0.0000

Data Index: 449226 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.2177. Min Act: -0.0001

Data Index: 1626780 (Python Code)

Max Activating Token Index: 558

Text #11

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.1634. Min Act: -0.0001

Data Index: 527688 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.1384. Min Act: -0.0001

Data Index: 236796 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.0792. Min Act: -0.0001

Data Index: 612165 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.0870. Min Act: -0.0000

Data Index: 580258 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.0670. Min Act: -0.0001

Data Index: 1009214 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.0640. Min Act: -0.0001

Data Index: 116450 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.1261. Min Act: -0.0001

Data Index: 759702 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 1.6951. Min Range: -1.6951

Max Act: 0.9969. Min Act: -0.0000

Data Index: 839981 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 1.6951. Min Range: -1.6951

Max Act: 1.0398. Min Act: -0.0000

Data Index: 1400004 (Python Code)

Max Activating Token Index: 19