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

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

Neuron 3207 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.7477. Min Act: -0.0001

Data Index: 618094 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6812. Min Act: -0.0001

Data Index: 1304220 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.6188. Min Act: -0.0001

Data Index: 618207 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.5725. Min Act: -0.0001

Data Index: 1110325 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.5316. Min Act: -0.0001

Data Index: 55115 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.5451. Min Act: -0.0001

Data Index: 164463 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.4922. Min Act: -0.0001

Data Index: 1126390 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.5007. Min Act: -0.0001

Data Index: 425322 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.5181. Min Act: -0.0001

Data Index: 1099327 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.5530. Min Act: -0.0001

Data Index: 708137 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.5245. Min Act: -0.0001

Data Index: 1082720 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.5000. Min Act: -0.0001

Data Index: 671169 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.4960. Min Act: -0.0001

Data Index: 156230 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.5054. Min Act: -0.0001

Data Index: 1212774 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.4608. Min Act: -0.0001

Data Index: 246399 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.4819. Min Act: -0.0001

Data Index: 96544 (C4 (Web Text))

Max Activating Token Index: 324

Text #16

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.4659. Min Act: -0.0001

Data Index: 970971 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.4941. Min Act: -0.0001

Data Index: 521105 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.4731. Min Act: -0.0001

Data Index: 648717 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.7477. Min Range: -0.7477

Max Act: 0.4851. Min Act: -0.0001

Data Index: 267315 (C4 (Web Text))

Max Activating Token Index: 970