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

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

Neuron 1942 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.6989. Min Act: -0.0001

Data Index: 1346659 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.4351. Min Act: -0.0000

Data Index: 53897 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.2883. Min Act: -0.0000

Data Index: 1037208 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.4406. Min Act: -0.0000

Data Index: 895339 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.3831. Min Act: -0.0000

Data Index: 974813 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.3608. Min Act: -0.0000

Data Index: 1241181 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.3345. Min Act: -0.0001

Data Index: 693077 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.3164. Min Act: -0.0000

Data Index: 801990 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.2562. Min Act: -0.0001

Data Index: 970479 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.2801. Min Act: -0.0000

Data Index: 685758 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.2771. Min Act: -0.0000

Data Index: 1308910 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.2775. Min Act: -0.0000

Data Index: 771040 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.1844. Min Act: -0.0000

Data Index: 1143593 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.2390. Min Act: -0.0000

Data Index: 260923 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1289030 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.1197. Min Act: -0.0001

Data Index: 551900 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.0625. Min Act: -0.0001

Data Index: 1145639 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.1618. Min Act: -0.0001

Data Index: 1318161 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.1638. Min Act: -0.0001

Data Index: 273534 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 1.6989. Min Range: -1.6989

Max Act: 1.0688. Min Act: -0.0001

Data Index: 415400 (C4 (Web Text))

Max Activating Token Index: 302