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

Dataset: The Pile

Neuron 1509 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1258524 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.5392. Min Act: -0.0000

Data Index: 394503 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1139572 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1628356 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4522. Min Act: -0.0000

Data Index: 307883 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1187274 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1513033 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4750. Min Act: -0.0000

Data Index: 686633 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4515. Min Act: -0.0000

Data Index: 840112 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1844504 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4399. Min Act: -0.0000

Data Index: 1464304 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4397. Min Act: -0.0000

Data Index: 93405 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3995. Min Act: -0.0000

Data Index: 860514 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1487827 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4078. Min Act: 0.0000

Data Index: 1569109 (The Pile)

Max Activating Token Index: 274

Text #15

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1200282 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1242616 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3872. Min Act: -0.0000

Data Index: 704363 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1789851 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 0.5475. Min Range: -0.5475

Max Act: 0.3805. Min Act: -0.0000

Data Index: 547203 (The Pile)

Max Activating Token Index: 305