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

Dataset: The Pile

Neuron 421 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: 0.4876. Min Range: -0.4876

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1567413 (The Pile)

Max Activating Token Index: 570

Text #1

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1017609 (The Pile)

Max Activating Token Index: 612

Text #2

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4082. Min Act: -0.0000

Data Index: 202934 (The Pile)

Max Activating Token Index: 73

Text #3

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3925. Min Act: -0.0000

Data Index: 777981 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4059. Min Act: -0.0000

Data Index: 489839 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3225. Min Act: -0.0000

Data Index: 542565 (The Pile)

Max Activating Token Index: 777

Text #6

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3594. Min Act: -0.0000

Data Index: 637432 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1905555 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3292. Min Act: -0.0000

Data Index: 258263 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3206. Min Act: -0.0000

Data Index: 128367 (The Pile)

Max Activating Token Index: 487

Text #10

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1931932 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3504. Min Act: -0.0000

Data Index: 377085 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1493745 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1358125 (The Pile)

Max Activating Token Index: 489

Text #14

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3052. Min Act: -0.0000

Data Index: 653161 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3280. Min Act: -0.0000

Data Index: 303254 (The Pile)

Max Activating Token Index: 677

Text #16

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3171. Min Act: -0.0000

Data Index: 815736 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3179. Min Act: -0.0000

Data Index: 325270 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.2961. Min Act: -0.0000

Data Index: 484293 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3028. Min Act: -0.0000

Data Index: 904196 (The Pile)

Max Activating Token Index: 290