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

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

Neuron 5600 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: 2.4835. Min Range: -2.4835

Max Act: 2.4835. Min Act: -0.0000

Data Index: 1336179 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 2.4835. Min Range: -2.4835

Max Act: 2.1227. Min Act: -0.0000

Data Index: 83815 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 2.4835. Min Range: -2.4835

Max Act: 2.0663. Min Act: -0.0000

Data Index: 1355412 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.9846. Min Act: -0.0000

Data Index: 90675 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.9990. Min Act: -0.0000

Data Index: 877833 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 2.4835. Min Range: -2.4835

Max Act: 2.0064. Min Act: -0.0000

Data Index: 525391 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 2.4835. Min Range: -2.4835

Max Act: 2.0028. Min Act: -0.0000

Data Index: 712184 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.9883. Min Act: -0.0000

Data Index: 115768 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.9569. Min Act: -0.0000

Data Index: 728135 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 2.4835. Min Range: -2.4835

Max Act: 2.0353. Min Act: -0.0000

Data Index: 784159 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.8258. Min Act: -0.0000

Data Index: 433233 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.8039. Min Act: -0.0000

Data Index: 870894 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.6458. Min Act: -0.0000

Data Index: 701026 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.6215. Min Act: -0.0000

Data Index: 478512 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1168153 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.6922. Min Act: -0.0000

Data Index: 1152387 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.6377. Min Act: -0.0000

Data Index: 526094 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.6183. Min Act: -0.0000

Data Index: 662711 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.6556. Min Act: -0.0000

Data Index: 651904 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 2.4835. Min Range: -2.4835

Max Act: 1.5436. Min Act: -0.0000

Data Index: 513365 (C4 (Web Text))

Max Activating Token Index: 545