Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 794 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2277. Min Range: -2.2277

Max Act: 2.2277. Min Act: -0.0001

Data Index: 776685 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.8764. Min Act: -0.0000

Data Index: 739408 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.6788. Min Act: -0.0000

Data Index: 445462 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.6108. Min Act: -0.0001

Data Index: 917143 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.6850. Min Act: -0.0001

Data Index: 629196 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.4944. Min Act: -0.0000

Data Index: 1292200 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.5132. Min Act: -0.0000

Data Index: 1286536 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.5934. Min Act: -0.0001

Data Index: 954157 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.7703. Min Act: -0.0001

Data Index: 999891 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.6776. Min Act: -0.0000

Data Index: 482376 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.5479. Min Act: -0.0000

Data Index: 808589 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.3812. Min Act: -0.0001

Data Index: 512061 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.4319. Min Act: -0.0001

Data Index: 597791 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.5006. Min Act: -0.0000

Data Index: 354406 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.4015. Min Act: -0.0000

Data Index: 463403 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.4637. Min Act: -0.0001

Data Index: 473939 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.3893. Min Act: -0.0001

Data Index: 1168349 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.4634. Min Act: -0.0000

Data Index: 1149467 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.4560. Min Act: -0.0000

Data Index: 306313 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 2.2277. Min Range: -2.2277

Max Act: 1.3701. Min Act: -0.0001

Data Index: 733137 (C4 (Web Text))

Max Activating Token Index: 815