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

Dataset: The Pile

Neuron 3375 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: 0.7164. Min Range: -0.7164

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1018736 (The Pile)

Max Activating Token Index: 569

Text #1

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6091. Min Act: -0.0000

Data Index: 536011 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1146086 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.6363. Min Act: -0.0000

Data Index: 459284 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5835. Min Act: -0.0000

Data Index: 675020 (The Pile)

Max Activating Token Index: 269

Text #5

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1699327 (The Pile)

Max Activating Token Index: 460

Text #6

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5837. Min Act: -0.0000

Data Index: 309384 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1522495 (The Pile)

Max Activating Token Index: 189

Text #8

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5715. Min Act: -0.0000

Data Index: 81080 (The Pile)

Max Activating Token Index: 319

Text #9

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5412. Min Act: -0.0000

Data Index: 985342 (The Pile)

Max Activating Token Index: 920

Text #10

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1654789 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5385. Min Act: -0.0000

Data Index: 669871 (The Pile)

Max Activating Token Index: 649

Text #12

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1615183 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5329. Min Act: -0.0000

Data Index: 53907 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1176028 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5265. Min Act: -0.0000

Data Index: 591900 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1916852 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5344. Min Act: -0.0000

Data Index: 708958 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5307. Min Act: -0.0000

Data Index: 909846 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 0.7164. Min Range: -0.7164

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1645861 (The Pile)

Max Activating Token Index: 876