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

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

Neuron 2682 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: 0.5547. Min Range: -0.5547

Max Act: 0.5247. Min Act: -0.0000

Data Index: 228875 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5037. Min Act: -0.0000

Data Index: 726056 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5547. Min Act: -0.0001

Data Index: 70376 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4961. Min Act: -0.0000

Data Index: 617087 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1017634 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1159557 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4592. Min Act: -0.0000

Data Index: 577472 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4834. Min Act: -0.0000

Data Index: 272027 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4822. Min Act: -0.0000

Data Index: 450847 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4735. Min Act: -0.0001

Data Index: 370922 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1021602 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4441. Min Act: -0.0000

Data Index: 691904 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4123. Min Act: -0.0001

Data Index: 645551 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4273. Min Act: -0.0000

Data Index: 658389 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4128. Min Act: -0.0000

Data Index: 865976 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4356. Min Act: -0.0000

Data Index: 362725 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3973. Min Act: -0.0000

Data Index: 636396 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4332. Min Act: -0.0000

Data Index: 32408 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4122. Min Act: -0.0000

Data Index: 270620 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4237. Min Act: -0.0001

Data Index: 440774 (C4 (Web Text))

Max Activating Token Index: 65