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

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

Neuron 1710 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.5223. Min Act: -0.0001

Data Index: 739742 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.5353. Min Act: -0.0001

Data Index: 546629 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4913. Min Act: -0.0001

Data Index: 1483334 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.5289. Min Act: -0.0001

Data Index: 1434654 (Python Code)

Max Activating Token Index: 308

Text #4

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.5087. Min Act: -0.0001

Data Index: 558823 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4710. Min Act: -0.0000

Data Index: 852970 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.5273. Min Act: -0.0001

Data Index: 727960 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.5072. Min Act: -0.0001

Data Index: 160309 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4833. Min Act: -0.0001

Data Index: 367661 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4818. Min Act: -0.0001

Data Index: 397547 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4908. Min Act: -0.0001

Data Index: 1113185 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4854. Min Act: -0.0001

Data Index: 836549 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4832. Min Act: -0.0001

Data Index: 667144 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4472. Min Act: -0.0001

Data Index: 1459718 (Python Code)

Max Activating Token Index: 712

Text #14

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4526. Min Act: -0.0001

Data Index: 657858 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4531. Min Act: -0.0001

Data Index: 464052 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4671. Min Act: -0.0001

Data Index: 230707 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4662. Min Act: -0.0001

Data Index: 586370 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4487. Min Act: -0.0001

Data Index: 1313592 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4330. Min Act: -0.0001

Data Index: 1434691 (Python Code)

Max Activating Token Index: 746