Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3628 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2900. Min Range: -2.2900

Max Act: 2.2900. Min Act: -0.0000

Data Index: 1167842 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 2.2900. Min Range: -2.2900

Max Act: 2.0487. Min Act: -0.0000

Data Index: 494130 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 2.2900. Min Range: -2.2900

Max Act: 2.1211. Min Act: -0.0000

Data Index: 1316638 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.9880. Min Act: -0.0000

Data Index: 807620 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.9542. Min Act: -0.0000

Data Index: 809793 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.9471. Min Act: -0.0000

Data Index: 1335209 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.9413. Min Act: -0.0000

Data Index: 1083719 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.6737. Min Act: -0.0000

Data Index: 515622 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.6554. Min Act: -0.0000

Data Index: 953592 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.6153. Min Act: -0.0000

Data Index: 643888 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.5766. Min Act: -0.0000

Data Index: 689594 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1025288 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.4573. Min Act: -0.0000

Data Index: 219977 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.5092. Min Act: -0.0000

Data Index: 784566 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.5978. Min Act: -0.0000

Data Index: 946014 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.4103. Min Act: -0.0000

Data Index: 96679 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.4768. Min Act: -0.0000

Data Index: 928062 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.4294. Min Act: -0.0000

Data Index: 678449 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.4247. Min Act: -0.0000

Data Index: 434522 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 2.2900. Min Range: -2.2900

Max Act: 1.4154. Min Act: -0.0000

Data Index: 362832 (C4 (Web Text))

Max Activating Token Index: 43