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

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

Neuron 5033 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.7940. Min Act: -0.0000

Data Index: 298001 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 2.7940. Min Range: -2.7940

Max Act: 2.0872. Min Act: -0.0000

Data Index: 796583 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.9947. Min Act: -0.0000

Data Index: 1359252 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.9314. Min Act: 0.0001

Data Index: 744943 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.8378. Min Act: -0.0000

Data Index: 97407 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.7965. Min Act: -0.0000

Data Index: 440160 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.7902. Min Act: -0.0000

Data Index: 1271554 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.7766. Min Act: -0.0000

Data Index: 1194324 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.8553. Min Act: -0.0000

Data Index: 1138184 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.6520. Min Act: -0.0000

Data Index: 4751 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.5761. Min Act: -0.0000

Data Index: 216004 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.7975. Min Act: -0.0000

Data Index: 951895 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.3932. Min Act: -0.0000

Data Index: 1171100 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.5214. Min Act: -0.0000

Data Index: 509395 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.4846. Min Act: 0.0000

Data Index: 559394 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.4467. Min Act: -0.0000

Data Index: 169428 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.4424. Min Act: -0.0000

Data Index: 1271749 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.5281. Min Act: -0.0000

Data Index: 642538 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.4052. Min Act: -0.0000

Data Index: 393077 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 2.7940. Min Range: -2.7940

Max Act: 1.4800. Min Act: -0.0000

Data Index: 425663 (C4 (Web Text))

Max Activating Token Index: 365