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

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

Neuron 5197 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: 0.6050. Min Range: -0.6050

Max Act: 0.6050. Min Act: -0.0000

Data Index: 743010 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5454. Min Act: -0.0000

Data Index: 973331 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5199. Min Act: -0.0000

Data Index: 95601 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1036991 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1300857 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1105824 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4699. Min Act: -0.0000

Data Index: 427409 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4534. Min Act: -0.0000

Data Index: 508365 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4502. Min Act: 0.0000

Data Index: 1182093 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1255417 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4597. Min Act: 0.0000

Data Index: 1313071 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4756. Min Act: -0.0000

Data Index: 690346 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4640. Min Act: -0.0000

Data Index: 698138 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4589. Min Act: -0.0000

Data Index: 986087 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4521. Min Act: -0.0000

Data Index: 172217 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4485. Min Act: -0.0000

Data Index: 219246 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4457. Min Act: -0.0000

Data Index: 807596 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4439. Min Act: 0.0000

Data Index: 497404 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4214. Min Act: 0.0000

Data Index: 1249818 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.6050. Min Range: -0.6050

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1052529 (C4 (Web Text))

Max Activating Token Index: 768