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

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

Neuron 4815 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.5445. Min Act: -0.0000

Data Index: 643148 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.5601. Min Act: -0.0000

Data Index: 992780 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4985. Min Act: -0.0000

Data Index: 189102 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1054231 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1031265 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4443. Min Act: -0.0000

Data Index: 947848 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4615. Min Act: -0.0000

Data Index: 916410 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4292. Min Act: -0.0000

Data Index: 249783 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4418. Min Act: -0.0000

Data Index: 916133 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4246. Min Act: -0.0000

Data Index: 786265 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4800. Min Act: -0.0000

Data Index: 947960 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4159. Min Act: -0.0000

Data Index: 1339353 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4423. Min Act: -0.0000

Data Index: 33881 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4309. Min Act: -0.0000

Data Index: 485731 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.3938. Min Act: -0.0000

Data Index: 389701 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4082. Min Act: -0.0000

Data Index: 889307 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4229. Min Act: -0.0000

Data Index: 883427 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.4206. Min Act: -0.0000

Data Index: 108014 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.3901. Min Act: -0.0000

Data Index: 707223 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.5601. Min Range: -0.5601

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1247547 (C4 (Web Text))

Max Activating Token Index: 902