Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2546 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.6330. Min Act: -0.0001

Data Index: 1142165 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.6147. Min Act: -0.0001

Data Index: 157915 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5480. Min Act: -0.0001

Data Index: 209609 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.6117. Min Act: -0.0001

Data Index: 634210 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5083. Min Act: -0.0000

Data Index: 905535 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5493. Min Act: -0.0001

Data Index: 670746 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5379. Min Act: -0.0001

Data Index: 467987 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4885. Min Act: -0.0001

Data Index: 393296 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4890. Min Act: -0.0001

Data Index: 168142 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4971. Min Act: -0.0000

Data Index: 327067 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5290. Min Act: -0.0000

Data Index: 918961 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5627. Min Act: -0.0001

Data Index: 1289307 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4650. Min Act: -0.0001

Data Index: 970413 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4601. Min Act: -0.0001

Data Index: 907043 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.5069. Min Act: -0.0000

Data Index: 409320 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4748. Min Act: -0.0001

Data Index: 1050456 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4312. Min Act: -0.0000

Data Index: 728738 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1303296 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4010. Min Act: -0.0000

Data Index: 186897 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.6330. Min Range: -0.6330

Max Act: 0.4901. Min Act: -0.0000

Data Index: 667717 (C4 (Web Text))

Max Activating Token Index: 664