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

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

Neuron 5525 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.5382. Min Act: -0.0000

Data Index: 409521 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1059753 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1173703 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.3922. Min Act: -0.0000

Data Index: 1519808 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.3752. Min Act: -0.0000

Data Index: 846101 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.3648. Min Act: -0.0000

Data Index: 935916 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.3173. Min Act: -0.0000

Data Index: 910407 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1454295 (Python Code)

Max Activating Token Index: 697

Text #8

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.3027. Min Act: -0.0000

Data Index: 1438108 (Python Code)

Max Activating Token Index: 854

Text #9

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.3045. Min Act: -0.0000

Data Index: 943358 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.3055. Min Act: -0.0000

Data Index: 317786 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.2996. Min Act: -0.0000

Data Index: 1213901 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1212256 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.2909. Min Act: -0.0000

Data Index: 170960 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.2887. Min Act: -0.0000

Data Index: 56133 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1018975 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1005807 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1005721 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.2969. Min Act: -0.0000

Data Index: 847421 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.5382. Min Range: -0.5382

Max Act: 0.2978. Min Act: -0.0000

Data Index: 447759 (C4 (Web Text))

Max Activating Token Index: 971