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

Dataset: The Pile

Neuron 3386 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: 1.7825. Min Range: -1.7825

Max Act: 1.7534. Min Act: -0.0000

Data Index: 881407 (The Pile)

Max Activating Token Index: 915

Text #1

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.7825. Min Act: -0.0000

Data Index: 230240 (The Pile)

Max Activating Token Index: 62

Text #2

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5861. Min Act: -0.0000

Data Index: 463262 (The Pile)

Max Activating Token Index: 376

Text #3

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.6389. Min Act: -0.0000

Data Index: 1307423 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1329554 (The Pile)

Max Activating Token Index: 275

Text #5

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5887. Min Act: -0.0000

Data Index: 577559 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5778. Min Act: -0.0000

Data Index: 1553971 (The Pile)

Max Activating Token Index: 936

Text #7

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.4749. Min Act: -0.0000

Data Index: 1493168 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.5171. Min Act: -0.0000

Data Index: 1456595 (The Pile)

Max Activating Token Index: 281

Text #9

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1325256 (The Pile)

Max Activating Token Index: 535

Text #10

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.3725. Min Act: -0.0000

Data Index: 712630 (The Pile)

Max Activating Token Index: 753

Text #11

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.3749. Min Act: -0.0000

Data Index: 1270441 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.3585. Min Act: -0.0000

Data Index: 977237 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.3529. Min Act: -0.0000

Data Index: 792898 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.3316. Min Act: -0.0000

Data Index: 231654 (The Pile)

Max Activating Token Index: 589

Text #15

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.3171. Min Act: -0.0000

Data Index: 640313 (The Pile)

Max Activating Token Index: 893

Text #16

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.3170. Min Act: -0.0000

Data Index: 1088151 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1506108 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.2995. Min Act: -0.0000

Data Index: 1255768 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 1.7825. Min Range: -1.7825

Max Act: 1.2947. Min Act: 0.0000

Data Index: 986505 (The Pile)

Max Activating Token Index: 601