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

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

Neuron 1003 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.4735. Min Act: -0.0001

Data Index: 33538 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.4598. Min Act: -0.0000

Data Index: 540655 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.4190. Min Act: -0.0001

Data Index: 156341 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.4137. Min Act: -0.0001

Data Index: 118864 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.4036. Min Act: -0.0001

Data Index: 509715 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.4292. Min Act: -0.0000

Data Index: 75118 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3841. Min Act: -0.0001

Data Index: 765156 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3631. Min Act: -0.0000

Data Index: 352607 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3585. Min Act: -0.0000

Data Index: 733525 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1031741 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3722. Min Act: -0.0001

Data Index: 560142 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1057866 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1149435 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3447. Min Act: -0.0001

Data Index: 470439 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3584. Min Act: -0.0001

Data Index: 496548 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3493. Min Act: -0.0001

Data Index: 630740 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3459. Min Act: -0.0000

Data Index: 683845 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3456. Min Act: -0.0001

Data Index: 852857 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3555. Min Act: -0.0000

Data Index: 973854 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.4735. Min Range: -0.4735

Max Act: 0.3321. Min Act: -0.0000

Data Index: 549365 (C4 (Web Text))

Max Activating Token Index: 116