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

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

Neuron 1998 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3432. Min Range: -3.3432

Max Act: 3.3432. Min Act: -0.0000

Data Index: 944251 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.7048. Min Act: -0.0000

Data Index: 762825 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.8698. Min Act: -0.0000

Data Index: 1392289 (Python Code)

Max Activating Token Index: 433

Text #3

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.5277. Min Act: -0.0000

Data Index: 1502146 (Python Code)

Max Activating Token Index: 221

Text #4

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.6053. Min Act: -0.0000

Data Index: 1192670 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.7183. Min Act: -0.0000

Data Index: 1554105 (Python Code)

Max Activating Token Index: 511

Text #6

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.5467. Min Act: -0.0000

Data Index: 149435 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.5476. Min Act: -0.0000

Data Index: 1303042 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.5023. Min Act: -0.0000

Data Index: 966695 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.3577. Min Act: -0.0000

Data Index: 795450 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.3513. Min Act: -0.0000

Data Index: 818558 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.4808. Min Act: -0.0000

Data Index: 165522 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.2115. Min Act: -0.0000

Data Index: 1327099 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 3.3432. Min Range: -3.3432

Max Act: 1.9642. Min Act: -0.0000

Data Index: 321155 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.4182. Min Act: -0.0000

Data Index: 630753 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.4126. Min Act: -0.0000

Data Index: 1084898 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.3877. Min Act: -0.0000

Data Index: 549721 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.3907. Min Act: -0.0000

Data Index: 1044303 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.3593. Min Act: -0.0000

Data Index: 1313052 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 3.3432. Min Range: -3.3432

Max Act: 2.1351. Min Act: -0.0000

Data Index: 768677 (C4 (Web Text))

Max Activating Token Index: 669