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

Dataset: The Pile

Neuron 3085 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.7559. Min Act: -0.0000

Data Index: 377109 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6901. Min Act: -0.0000

Data Index: 61972 (The Pile)

Max Activating Token Index: 595

Text #2

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6589. Min Act: -0.0000

Data Index: 747595 (The Pile)

Max Activating Token Index: 402

Text #3

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6388. Min Act: -0.0000

Data Index: 867334 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1344402 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1760643 (The Pile)

Max Activating Token Index: 397

Text #6

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6497. Min Act: -0.0000

Data Index: 585107 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1875091 (The Pile)

Max Activating Token Index: 459

Text #8

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1369724 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6376. Min Act: -0.0000

Data Index: 567584 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1193162 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5995. Min Act: -0.0000

Data Index: 702154 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1294633 (The Pile)

Max Activating Token Index: 507

Text #13

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6306. Min Act: -0.0000

Data Index: 104899 (The Pile)

Max Activating Token Index: 277

Text #14

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5937. Min Act: -0.0000

Data Index: 657271 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1462891 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1868415 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.6098. Min Act: -0.0000

Data Index: 798079 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1701062 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 0.7559. Min Range: -0.7559

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1512676 (The Pile)

Max Activating Token Index: 126