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

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

Neuron 263 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0614. Min Range: -1.0614

Max Act: 1.0438. Min Act: -0.0001

Data Index: 1096174 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 1.0614. Min Range: -1.0614

Max Act: 1.0501. Min Act: -0.0001

Data Index: 808228 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 1.0614. Min Range: -1.0614

Max Act: 1.0614. Min Act: -0.0001

Data Index: 181540 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 1.0614. Min Range: -1.0614

Max Act: 1.0573. Min Act: -0.0001

Data Index: 436519 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 1.0614. Min Range: -1.0614

Max Act: 1.0126. Min Act: -0.0001

Data Index: 1250370 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9516. Min Act: -0.0001

Data Index: 658888 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9308. Min Act: -0.0001

Data Index: 1293467 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8357. Min Act: -0.0001

Data Index: 140098 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8728. Min Act: -0.0001

Data Index: 604867 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8760. Min Act: -0.0001

Data Index: 312084 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.6869. Min Act: -0.0001

Data Index: 238272 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.9099. Min Act: -0.0001

Data Index: 1126464 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.7945. Min Act: -0.0001

Data Index: 1318713 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8288. Min Act: -0.0001

Data Index: 260603 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8267. Min Act: -0.0001

Data Index: 920099 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8242. Min Act: -0.0001

Data Index: 310249 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8769. Min Act: -0.0001

Data Index: 1185168 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.8257. Min Act: -0.0001

Data Index: 253393 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.7338. Min Act: -0.0001

Data Index: 597686 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 1.0614. Min Range: -1.0614

Max Act: 0.7775. Min Act: -0.0001

Data Index: 1136166 (C4 (Web Text))

Max Activating Token Index: 772