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

Dataset: The Pile

Neuron 73 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: 0.4488. Min Range: -0.4488

Max Act: 0.4338. Min Act: 0.0000

Data Index: 1934366 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4488. Min Act: -0.0000

Data Index: 951614 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1511354 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1273014 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4113. Min Act: 0.0001

Data Index: 1466066 (The Pile)

Max Activating Token Index: 653

Text #5

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4003. Min Act: -0.0000

Data Index: 429526 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1418755 (The Pile)

Max Activating Token Index: 348

Text #7

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.4037. Min Act: -0.0000

Data Index: 603874 (The Pile)

Max Activating Token Index: 208

Text #8

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3958. Min Act: -0.0000

Data Index: 424771 (The Pile)

Max Activating Token Index: 705

Text #9

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3381. Min Act: -0.0000

Data Index: 344365 (The Pile)

Max Activating Token Index: 484

Text #10

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3250. Min Act: -0.0000

Data Index: 346262 (The Pile)

Max Activating Token Index: 544

Text #11

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3725. Min Act: -0.0000

Data Index: 330105 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1618945 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1288429 (The Pile)

Max Activating Token Index: 547

Text #14

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3516. Min Act: -0.0000

Data Index: 509401 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3357. Min Act: -0.0000

Data Index: 526030 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3334. Min Act: 0.0000

Data Index: 1565686 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3085. Min Act: 0.0000

Data Index: 790312 (The Pile)

Max Activating Token Index: 902

Text #18

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3063. Min Act: 0.0000

Data Index: 830190 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 0.4488. Min Range: -0.4488

Max Act: 0.3148. Min Act: -0.0000

Data Index: 959957 (The Pile)

Max Activating Token Index: 633