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

Dataset: The Pile

Neuron 419 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1173588 (The Pile)

Max Activating Token Index: 512

Text #1

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5402. Min Act: -0.0000

Data Index: 245970 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.5091. Min Act: -0.0000

Data Index: 672363 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1476751 (The Pile)

Max Activating Token Index: 621

Text #4

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4710. Min Act: -0.0000

Data Index: 223193 (The Pile)

Max Activating Token Index: 913

Text #5

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1107657 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4578. Min Act: -0.0000

Data Index: 882663 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1228744 (The Pile)

Max Activating Token Index: 487

Text #8

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4374. Min Act: -0.0000

Data Index: 165689 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4396. Min Act: -0.0000

Data Index: 987297 (The Pile)

Max Activating Token Index: 273

Text #10

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1030135 (The Pile)

Max Activating Token Index: 495

Text #11

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1186913 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4569. Min Act: -0.0000

Data Index: 1689643 (The Pile)

Max Activating Token Index: 810

Text #13

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4433. Min Act: -0.0000

Data Index: 241110 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4145. Min Act: -0.0000

Data Index: 640315 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1399196 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1232385 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1639063 (The Pile)

Max Activating Token Index: 972

Text #18

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1506761 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 0.5425. Min Range: -0.5425

Max Act: 0.4328. Min Act: -0.0000

Data Index: 155497 (The Pile)

Max Activating Token Index: 458