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

Dataset: The Pile

Neuron 3582 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1977255 (The Pile)

Max Activating Token Index: 558

Text #1

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1716158 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2669. Min Act: -0.0000

Data Index: 370262 (The Pile)

Max Activating Token Index: 837

Text #3

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2513. Min Act: 0.0000

Data Index: 1308485 (The Pile)

Max Activating Token Index: 96

Text #4

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1481080 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2428. Min Act: -0.0000

Data Index: 269041 (The Pile)

Max Activating Token Index: 640

Text #6

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2511. Min Act: -0.0000

Data Index: 1068481 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2387. Min Act: -0.0000

Data Index: 1832651 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2285. Min Act: -0.0000

Data Index: 580314 (The Pile)

Max Activating Token Index: 833

Text #9

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2363. Min Act: -0.0000

Data Index: 1923645 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1095126 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2505. Min Act: -0.0000

Data Index: 572735 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2225. Min Act: 0.0000

Data Index: 682667 (The Pile)

Max Activating Token Index: 865

Text #13

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1332837 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1276119 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2118. Min Act: -0.0000

Data Index: 592568 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2233. Min Act: -0.0000

Data Index: 531950 (The Pile)

Max Activating Token Index: 502

Text #17

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1630392 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2156. Min Act: -0.0000

Data Index: 564695 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1718307 (The Pile)

Max Activating Token Index: 407