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

Dataset: The Pile

Neuron 2452 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: 0.9348. Min Range: -0.9348

Max Act: 0.9276. Min Act: -0.0000

Data Index: 271523 (The Pile)

Max Activating Token Index: 923

Text #1

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.9348. Min Act: -0.0000

Data Index: 4523 (The Pile)

Max Activating Token Index: 39

Text #2

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1796682 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.9251. Min Act: -0.0000

Data Index: 197931 (The Pile)

Max Activating Token Index: 453

Text #4

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8854. Min Act: -0.0000

Data Index: 279249 (The Pile)

Max Activating Token Index: 415

Text #5

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1064029 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8003. Min Act: -0.0000

Data Index: 896994 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8203. Min Act: -0.0000

Data Index: 989332 (The Pile)

Max Activating Token Index: 425

Text #8

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8249. Min Act: -0.0000

Data Index: 643760 (The Pile)

Max Activating Token Index: 599

Text #9

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8046. Min Act: -0.0000

Data Index: 1119653 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8699. Min Act: -0.0000

Data Index: 255640 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1072722 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8361. Min Act: -0.0000

Data Index: 209844 (The Pile)

Max Activating Token Index: 445

Text #13

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.9082. Min Act: -0.0000

Data Index: 539594 (The Pile)

Max Activating Token Index: 138

Text #14

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8705. Min Act: -0.0000

Data Index: 257023 (The Pile)

Max Activating Token Index: 858

Text #15

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7793. Min Act: -0.0000

Data Index: 741479 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1603807 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8544. Min Act: -0.0000

Data Index: 547478 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.8361. Min Act: -0.0000

Data Index: 562458 (The Pile)

Max Activating Token Index: 436

Text #19

Max Range: 0.9348. Min Range: -0.9348

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1724356 (The Pile)

Max Activating Token Index: 475