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

Dataset: The Pile

Neuron 4127 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.6559. Min Act: -0.0000

Data Index: 626094 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.6041. Min Act: -0.0000

Data Index: 1686633 (The Pile)

Max Activating Token Index: 230

Text #2

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.5284. Min Act: -0.0000

Data Index: 353938 (The Pile)

Max Activating Token Index: 489

Text #3

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.5362. Min Act: -0.0000

Data Index: 1863116 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.4288. Min Act: -0.0000

Data Index: 244273 (The Pile)

Max Activating Token Index: 852

Text #5

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.5011. Min Act: -0.0000

Data Index: 486195 (The Pile)

Max Activating Token Index: 591

Text #6

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.4870. Min Act: -0.0000

Data Index: 1231872 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.4414. Min Act: -0.0000

Data Index: 1461849 (The Pile)

Max Activating Token Index: 444

Text #8

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.3603. Min Act: -0.0000

Data Index: 845298 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.5267. Min Act: -0.0000

Data Index: 1178722 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.4485. Min Act: -0.0000

Data Index: 1918035 (The Pile)

Max Activating Token Index: 134

Text #11

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.3861. Min Act: -0.0000

Data Index: 1025439 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.5050. Min Act: -0.0000

Data Index: 1353910 (The Pile)

Max Activating Token Index: 621

Text #13

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.4518. Min Act: -0.0000

Data Index: 142856 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.4074. Min Act: -0.0000

Data Index: 209409 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.4024. Min Act: -0.0000

Data Index: 549362 (The Pile)

Max Activating Token Index: 451

Text #16

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.4885. Min Act: -0.0000

Data Index: 1715707 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.4253. Min Act: -0.0000

Data Index: 509601 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.3508. Min Act: -0.0000

Data Index: 1491570 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 1.6559. Min Range: -1.6559

Max Act: 1.3205. Min Act: -0.0000

Data Index: 1207928 (The Pile)

Max Activating Token Index: 747