Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4865 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1675843 (The Pile)

Max Activating Token Index: 616

Text #1

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1068836 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1761522 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2489. Min Act: -0.0000

Data Index: 930078 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2419. Min Act: -0.0000

Data Index: 218848 (The Pile)

Max Activating Token Index: 713

Text #5

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2335. Min Act: -0.0000

Data Index: 257167 (The Pile)

Max Activating Token Index: 221

Text #6

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1837977 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2321. Min Act: -0.0000

Data Index: 32312 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1395349 (The Pile)

Max Activating Token Index: 384

Text #9

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2197. Min Act: -0.0000

Data Index: 275661 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2146. Min Act: -0.0000

Data Index: 1003152 (The Pile)

Max Activating Token Index: 669

Text #11

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2162. Min Act: -0.0000

Data Index: 373922 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1330327 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2075. Min Act: -0.0000

Data Index: 207604 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2100. Min Act: -0.0000

Data Index: 36684 (The Pile)

Max Activating Token Index: 254

Text #15

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2144. Min Act: -0.0000

Data Index: 652037 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2049. Min Act: -0.0000

Data Index: 705398 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1864018 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1747262 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1083373 (The Pile)

Max Activating Token Index: 349