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

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

Neuron 5941 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: 5.0501. Min Range: -5.0501

Max Act: 5.0391. Min Act: -0.0001

Data Index: 221964 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.5575. Min Act: -0.0000

Data Index: 1336510 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.8874. Min Act: -0.0000

Data Index: 657301 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 5.0501. Min Range: -5.0501

Max Act: 5.0501. Min Act: -0.0000

Data Index: 913399 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.4663. Min Act: -0.0000

Data Index: 1337982 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.6438. Min Act: -0.0001

Data Index: 151087 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.6593. Min Act: -0.0001

Data Index: 349043 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.9700. Min Act: -0.0001

Data Index: 548838 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.7801. Min Act: -0.0001

Data Index: 899520 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.8787. Min Act: -0.0001

Data Index: 110672 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.4981. Min Act: -0.0000

Data Index: 1348181 (C4 (Web Text))

Max Activating Token Index: 897

Text #11

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.6269. Min Act: -0.0001

Data Index: 463897 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.4192. Min Act: -0.0001

Data Index: 96225 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.2283. Min Act: -0.0000

Data Index: 1000963 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.8981. Min Act: -0.0001

Data Index: 239104 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.7033. Min Act: -0.0001

Data Index: 292092 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.5012. Min Act: -0.0001

Data Index: 438515 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.3173. Min Act: -0.0000

Data Index: 846321 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.6369. Min Act: -0.0000

Data Index: 105823 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 5.0501. Min Range: -5.0501

Max Act: 4.2903. Min Act: -0.0001

Data Index: 1357251 (C4 (Web Text))

Max Activating Token Index: 226