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

Dataset: The Pile

Neuron 2545 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.4441. Min Act: -0.0000

Data Index: 683291 (The Pile)

Max Activating Token Index: 956

Text #1

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1014841 (The Pile)

Max Activating Token Index: 838

Text #2

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1449186 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3710. Min Act: -0.0000

Data Index: 354201 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3356. Min Act: -0.0000

Data Index: 352634 (The Pile)

Max Activating Token Index: 234

Text #5

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1644831 (The Pile)

Max Activating Token Index: 317

Text #6

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1247869 (The Pile)

Max Activating Token Index: 185

Text #7

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3547. Min Act: -0.0000

Data Index: 1890402 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3424. Min Act: -0.0000

Data Index: 219723 (The Pile)

Max Activating Token Index: 210

Text #9

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3431. Min Act: -0.0000

Data Index: 123459 (The Pile)

Max Activating Token Index: 525

Text #10

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1537611 (The Pile)

Max Activating Token Index: 285

Text #11

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1624814 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1364699 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3277. Min Act: -0.0000

Data Index: 1386012 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3134. Min Act: -0.0000

Data Index: 145908 (The Pile)

Max Activating Token Index: 883

Text #15

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3312. Min Act: -0.0000

Data Index: 349655 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3299. Min Act: -0.0000

Data Index: 730802 (The Pile)

Max Activating Token Index: 89

Text #17

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3174. Min Act: -0.0000

Data Index: 968852 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3290. Min Act: -0.0000

Data Index: 619 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 0.4441. Min Range: -0.4441

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1275380 (The Pile)

Max Activating Token Index: 325