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

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

Neuron 5771 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: 0.8960. Min Range: -0.8960

Max Act: 0.8960. Min Act: -0.0000

Data Index: 1188269 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8876. Min Act: -0.0000

Data Index: 676188 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.8113. Min Act: -0.0000

Data Index: 212213 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7999. Min Act: -0.0000

Data Index: 601222 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1152785 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7233. Min Act: -0.0000

Data Index: 623075 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7212. Min Act: -0.0000

Data Index: 1152354 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6705. Min Act: -0.0000

Data Index: 66009 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7156. Min Act: -0.0000

Data Index: 341615 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6685. Min Act: -0.0000

Data Index: 110842 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6813. Min Act: -0.0000

Data Index: 896174 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6267. Min Act: -0.0000

Data Index: 386190 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1084061 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6254. Min Act: -0.0000

Data Index: 403675 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6220. Min Act: -0.0000

Data Index: 28445 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1122717 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6226. Min Act: -0.0000

Data Index: 544416 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6167. Min Act: -0.0000

Data Index: 97909 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6570. Min Act: -0.0000

Data Index: 256100 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.8960. Min Range: -0.8960

Max Act: 0.6520. Min Act: -0.0000

Data Index: 954918 (C4 (Web Text))

Max Activating Token Index: 850