Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2928 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0980. Min Range: -1.0980

Max Act: 1.0980. Min Act: -0.0001

Data Index: 471735 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.0980. Min Range: -1.0980

Max Act: 1.0738. Min Act: -0.0001

Data Index: 1039394 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.9752. Min Act: -0.0001

Data Index: 903228 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.9366. Min Act: -0.0001

Data Index: 1181419 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.9164. Min Act: -0.0001

Data Index: 1451921 (Python Code)

Max Activating Token Index: 251

Text #5

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.9030. Min Act: -0.0001

Data Index: 196341 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8975. Min Act: -0.0001

Data Index: 728131 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8720. Min Act: -0.0001

Data Index: 485716 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8261. Min Act: -0.0001

Data Index: 173414 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8122. Min Act: -0.0001

Data Index: 1575022 (Python Code)

Max Activating Token Index: 817

Text #10

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8504. Min Act: -0.0001

Data Index: 1403736 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8476. Min Act: -0.0001

Data Index: 716433 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7896. Min Act: -0.0001

Data Index: 626076 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8935. Min Act: -0.0001

Data Index: 1338787 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8552. Min Act: -0.0001

Data Index: 1632954 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8281. Min Act: -0.0001

Data Index: 1333662 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8273. Min Act: -0.0001

Data Index: 1126999 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7922. Min Act: -0.0001

Data Index: 538615 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.8034. Min Act: -0.0001

Data Index: 1422856 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 1.0980. Min Range: -1.0980

Max Act: 0.7476. Min Act: -0.0001

Data Index: 589438 (C4 (Web Text))

Max Activating Token Index: 576