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

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

Neuron 4834 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6643. Min Act: -0.0000

Data Index: 184228 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5015. Min Act: -0.0000

Data Index: 650348 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4514. Min Act: -0.0000

Data Index: 579906 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4468. Min Act: -0.0000

Data Index: 197984 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1120824 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4050. Min Act: -0.0000

Data Index: 509491 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4155. Min Act: -0.0000

Data Index: 332425 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3975. Min Act: -0.0000

Data Index: 378542 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3837. Min Act: -0.0000

Data Index: 875028 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1301189 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3883. Min Act: 0.0000

Data Index: 530512 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3728. Min Act: -0.0000

Data Index: 864562 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1131928 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3810. Min Act: -0.0000

Data Index: 443835 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3597. Min Act: -0.0000

Data Index: 386063 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3554. Min Act: -0.0000

Data Index: 352551 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3493. Min Act: -0.0000

Data Index: 328186 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3517. Min Act: -0.0000

Data Index: 8256 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3546. Min Act: -0.0000

Data Index: 877802 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.3503. Min Act: -0.0000

Data Index: 180727 (C4 (Web Text))

Max Activating Token Index: 629