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

Dataset: The Pile

Neuron 1796 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: 0.4431. Min Range: -0.4431

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1911019 (The Pile)

Max Activating Token Index: 247

Text #1

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3856. Min Act: -0.0000

Data Index: 563542 (The Pile)

Max Activating Token Index: 590

Text #2

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4407. Min Act: -0.0000

Data Index: 212145 (The Pile)

Max Activating Token Index: 321

Text #3

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4078. Min Act: -0.0000

Data Index: 909946 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3752. Min Act: -0.0000

Data Index: 620143 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1355338 (The Pile)

Max Activating Token Index: 423

Text #6

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1322630 (The Pile)

Max Activating Token Index: 890

Text #7

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1509491 (The Pile)

Max Activating Token Index: 835

Text #8

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3990. Min Act: -0.0000

Data Index: 800089 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4043. Min Act: -0.0000

Data Index: 277269 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1267471 (The Pile)

Max Activating Token Index: 267

Text #11

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3990. Min Act: -0.0000

Data Index: 947767 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1410080 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4079. Min Act: -0.0000

Data Index: 38616 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3667. Min Act: -0.0000

Data Index: 458638 (The Pile)

Max Activating Token Index: 831

Text #15

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1747170 (The Pile)

Max Activating Token Index: 620

Text #16

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3839. Min Act: -0.0000

Data Index: 475297 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1605472 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3498. Min Act: -0.0000

Data Index: 575983 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1428535 (The Pile)

Max Activating Token Index: 740