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

Dataset: The Pile

Neuron 1712 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.3987. Min Act: -0.0000

Data Index: 1239413 (The Pile)

Max Activating Token Index: 883

Text #1

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1697133 (The Pile)

Max Activating Token Index: 416

Text #2

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.0747. Min Act: -0.0000

Data Index: 1625363 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.1761. Min Act: -0.0000

Data Index: 1522897 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1028348 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.0939. Min Act: -0.0000

Data Index: 1448613 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1367332 (The Pile)

Max Activating Token Index: 69

Text #7

Max Range: 1.3987. Min Range: -1.3987

Max Act: 1.0238. Min Act: -0.0000

Data Index: 1998046 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.9998. Min Act: -0.0001

Data Index: 1503990 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.9835. Min Act: -0.0000

Data Index: 216392 (The Pile)

Max Activating Token Index: 67

Text #10

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1239915 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.9750. Min Act: -0.0000

Data Index: 262866 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.8608. Min Act: -0.0000

Data Index: 532219 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.9347. Min Act: -0.0000

Data Index: 784118 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.8705. Min Act: -0.0000

Data Index: 446148 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1704171 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.8789. Min Act: -0.0000

Data Index: 514362 (The Pile)

Max Activating Token Index: 348

Text #17

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1151731 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.8671. Min Act: -0.0000

Data Index: 55751 (The Pile)

Max Activating Token Index: 563

Text #19

Max Range: 1.3987. Min Range: -1.3987

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1148042 (The Pile)

Max Activating Token Index: 750