Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 452 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.6272. Min Act: -0.0001

Data Index: 1360429 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5896. Min Act: -0.0001

Data Index: 1362771 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1544851 (Python Code)

Max Activating Token Index: 955

Text #3

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5183. Min Act: -0.0001

Data Index: 947196 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5009. Min Act: -0.0001

Data Index: 1420274 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5182. Min Act: -0.0001

Data Index: 1392185 (Python Code)

Max Activating Token Index: 967

Text #6

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5337. Min Act: -0.0001

Data Index: 1448456 (Python Code)

Max Activating Token Index: 593

Text #7

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5144. Min Act: -0.0001

Data Index: 1413217 (Python Code)

Max Activating Token Index: 429

Text #8

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1387183 (Python Code)

Max Activating Token Index: 503

Text #9

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5178. Min Act: -0.0001

Data Index: 1509220 (Python Code)

Max Activating Token Index: 557

Text #10

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5130. Min Act: -0.0001

Data Index: 1591520 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4994. Min Act: -0.0001

Data Index: 1653121 (Python Code)

Max Activating Token Index: 615

Text #12

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5136. Min Act: -0.0001

Data Index: 171608 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4806. Min Act: -0.0001

Data Index: 1492391 (Python Code)

Max Activating Token Index: 146

Text #14

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5107. Min Act: -0.0001

Data Index: 1459190 (Python Code)

Max Activating Token Index: 893

Text #15

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.5291. Min Act: -0.0001

Data Index: 1515554 (Python Code)

Max Activating Token Index: 730

Text #16

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4958. Min Act: -0.0001

Data Index: 1455520 (Python Code)

Max Activating Token Index: 105

Text #17

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4808. Min Act: -0.0001

Data Index: 1395241 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4940. Min Act: -0.0001

Data Index: 179446 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.6272. Min Range: -0.6272

Max Act: 0.4622. Min Act: -0.0001

Data Index: 1104493 (C4 (Web Text))

Max Activating Token Index: 566