Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1174 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1041. Min Act: -0.0002

Data Index: 348144 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1627167 (Python Code)

Max Activating Token Index: 422

Text #2

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1026. Min Act: -0.0002

Data Index: 505677 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1029230 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0953. Min Act: -0.0002

Data Index: 1341942 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0961. Min Act: -0.0001

Data Index: 922858 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1642253 (Python Code)

Max Activating Token Index: 473

Text #7

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0942. Min Act: -0.0002

Data Index: 485285 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0918. Min Act: -0.0003

Data Index: 1378996 (Python Code)

Max Activating Token Index: 329

Text #9

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1158579 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0913. Min Act: -0.0002

Data Index: 5548 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0941. Min Act: -0.0002

Data Index: 1570439 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0887. Min Act: -0.0002

Data Index: 352755 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0911. Min Act: 0.0002

Data Index: 1451582 (Python Code)

Max Activating Token Index: 988

Text #14

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0896. Min Act: -0.0002

Data Index: 683571 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0896. Min Act: -0.0001

Data Index: 900145 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1413688 (Python Code)

Max Activating Token Index: 175

Text #17

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0882. Min Act: -0.0002

Data Index: 691234 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1652129 (Python Code)

Max Activating Token Index: 117

Text #19

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1148957 (C4 (Web Text))

Max Activating Token Index: 726