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

Dataset: The Pile

Neuron 2599 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.3313. Min Act: -0.0000

Data Index: 235218 (The Pile)

Max Activating Token Index: 871

Text #1

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.3184. Min Act: -0.0000

Data Index: 1194832 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1542044 (The Pile)

Max Activating Token Index: 248

Text #3

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1400901 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1663468 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1853912 (The Pile)

Max Activating Token Index: 539

Text #6

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1248071 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1554787 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2695. Min Act: -0.0000

Data Index: 131279 (The Pile)

Max Activating Token Index: 280

Text #9

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2627. Min Act: -0.0000

Data Index: 724914 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1338563 (The Pile)

Max Activating Token Index: 306

Text #11

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1754200 (The Pile)

Max Activating Token Index: 669

Text #12

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2492. Min Act: -0.0000

Data Index: 996725 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1148687 (The Pile)

Max Activating Token Index: 560

Text #14

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2489. Min Act: -0.0000

Data Index: 188334 (The Pile)

Max Activating Token Index: 369

Text #15

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2457. Min Act: -0.0000

Data Index: 1207858 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1353480 (The Pile)

Max Activating Token Index: 317

Text #17

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2280. Min Act: -0.0000

Data Index: 722403 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1704838 (The Pile)

Max Activating Token Index: 706

Text #19

Max Range: 0.3313. Min Range: -0.3313

Max Act: 0.2355. Min Act: -0.0000

Data Index: 998371 (The Pile)

Max Activating Token Index: 493