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

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

Neuron 3861 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1366. Min Range: -1.1366

Max Act: 1.1366. Min Act: -0.0001

Data Index: 908095 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 1.1366. Min Range: -1.1366

Max Act: 1.0633. Min Act: -0.0001

Data Index: 634162 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 1.1366. Min Range: -1.1366

Max Act: 1.1094. Min Act: -0.0001

Data Index: 935509 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 1.1366. Min Range: -1.1366

Max Act: 1.0458. Min Act: -0.0001

Data Index: 593784 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 1.1366. Min Range: -1.1366

Max Act: 1.0426. Min Act: -0.0001

Data Index: 353291 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 1.1366. Min Range: -1.1366

Max Act: 1.1255. Min Act: -0.0001

Data Index: 517949 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9900. Min Act: -0.0001

Data Index: 1030513 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 1.1366. Min Range: -1.1366

Max Act: 1.0543. Min Act: -0.0001

Data Index: 469591 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 1.1366. Min Range: -1.1366

Max Act: 1.0038. Min Act: -0.0001

Data Index: 140614 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9214. Min Act: -0.0001

Data Index: 1252290 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9547. Min Act: -0.0001

Data Index: 507408 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9120. Min Act: -0.0001

Data Index: 546438 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9899. Min Act: -0.0001

Data Index: 632035 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8591. Min Act: -0.0001

Data Index: 828254 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8856. Min Act: -0.0001

Data Index: 1309341 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.9274. Min Act: -0.0001

Data Index: 943470 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8820. Min Act: -0.0001

Data Index: 118767 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8896. Min Act: -0.0001

Data Index: 684681 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8770. Min Act: -0.0001

Data Index: 922335 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 1.1366. Min Range: -1.1366

Max Act: 0.8923. Min Act: -0.0001

Data Index: 1260277 (C4 (Web Text))

Max Activating Token Index: 283