Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3491 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.7080. Min Act: -0.0000

Data Index: 38333 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.6844. Min Act: -0.0000

Data Index: 134235 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.4014. Min Act: -0.0000

Data Index: 748415 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3744. Min Act: -0.0000

Data Index: 1148668 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3193. Min Act: -0.0000

Data Index: 856240 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.4037. Min Act: -0.0000

Data Index: 1262941 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3051. Min Act: -0.0000

Data Index: 407273 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2179. Min Act: -0.0000

Data Index: 238284 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2535. Min Act: -0.0000

Data Index: 707115 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.3233. Min Act: -0.0000

Data Index: 1317280 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2208. Min Act: -0.0000

Data Index: 480319 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1362679 (Python Code)

Max Activating Token Index: 165

Text #12

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2500. Min Act: -0.0000

Data Index: 1173547 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2436. Min Act: -0.0000

Data Index: 983438 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2709. Min Act: -0.0000

Data Index: 48380 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1648013 (Python Code)

Max Activating Token Index: 166

Text #16

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.1347. Min Act: -0.0000

Data Index: 345085 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.1365. Min Act: -0.0000

Data Index: 1206485 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.1272. Min Act: -0.0000

Data Index: 51459 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.1121. Min Act: -0.0000

Data Index: 655166 (C4 (Web Text))

Max Activating Token Index: 591