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

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

Neuron 5907 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: 1.1802. Min Range: -1.1802

Max Act: 1.1503. Min Act: -0.0000

Data Index: 1197858 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 1.1802. Min Range: -1.1802

Max Act: 1.1802. Min Act: -0.0000

Data Index: 1240489 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 1.1802. Min Range: -1.1802

Max Act: 1.1410. Min Act: -0.0000

Data Index: 851618 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 1.1802. Min Range: -1.1802

Max Act: 1.1156. Min Act: -0.0000

Data Index: 637335 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 1.1802. Min Range: -1.1802

Max Act: 1.0250. Min Act: -0.0000

Data Index: 659233 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 1.1802. Min Range: -1.1802

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1277083 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.9619. Min Act: -0.0000

Data Index: 126959 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1174208 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8918. Min Act: -0.0000

Data Index: 628904 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8625. Min Act: -0.0000

Data Index: 297957 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8390. Min Act: -0.0000

Data Index: 75525 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8428. Min Act: -0.0000

Data Index: 193100 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1304275 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1288141 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7684. Min Act: -0.0000

Data Index: 207129 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8107. Min Act: -0.0000

Data Index: 342597 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8093. Min Act: -0.0000

Data Index: 184441 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1350587 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7459. Min Act: -0.0000

Data Index: 528254 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1351327 (C4 (Web Text))

Max Activating Token Index: 38