Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3507 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.6015. Min Act: -0.0001

Data Index: 608805 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.4967. Min Act: -0.0001

Data Index: 456765 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.4841. Min Act: -0.0001

Data Index: 269051 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.3552. Min Act: -0.0001

Data Index: 1055685 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.4374. Min Act: -0.0001

Data Index: 517672 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.3347. Min Act: -0.0001

Data Index: 700880 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.2465. Min Act: -0.0001

Data Index: 842740 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.3347. Min Act: -0.0001

Data Index: 862682 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.2615. Min Act: -0.0001

Data Index: 1275482 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.2897. Min Act: -0.0001

Data Index: 213087 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.1494. Min Act: -0.0001

Data Index: 740238 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.1734. Min Act: -0.0001

Data Index: 669335 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.1561. Min Act: -0.0001

Data Index: 657811 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.0871. Min Act: -0.0001

Data Index: 926886 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.1469. Min Act: -0.0001

Data Index: 1346253 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.2032. Min Act: -0.0001

Data Index: 859377 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.1454. Min Act: -0.0001

Data Index: 24504 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.1290. Min Act: -0.0001

Data Index: 72400 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.1201. Min Act: -0.0001

Data Index: 199432 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 1.6015. Min Range: -1.6015

Max Act: 1.0644. Min Act: -0.0001

Data Index: 93332 (C4 (Web Text))

Max Activating Token Index: 325