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

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

Neuron 2686 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: 0.4273. Min Range: -0.4273

Max Act: 0.4179. Min Act: -0.0001

Data Index: 544046 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.4273. Min Act: -0.0001

Data Index: 1167235 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.4056. Min Act: -0.0001

Data Index: 129767 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.4013. Min Act: -0.0001

Data Index: 1221882 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.4145. Min Act: -0.0001

Data Index: 684700 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3916. Min Act: -0.0001

Data Index: 1178950 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.4026. Min Act: -0.0001

Data Index: 815665 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3866. Min Act: -0.0001

Data Index: 50849 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3904. Min Act: -0.0001

Data Index: 807325 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3745. Min Act: -0.0001

Data Index: 1333059 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3734. Min Act: -0.0001

Data Index: 665912 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3851. Min Act: -0.0001

Data Index: 63562 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3558. Min Act: -0.0001

Data Index: 679348 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3660. Min Act: -0.0001

Data Index: 668163 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3747. Min Act: -0.0001

Data Index: 581850 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3877. Min Act: -0.0001

Data Index: 1078676 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3899. Min Act: -0.0001

Data Index: 530087 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3589. Min Act: -0.0001

Data Index: 14153 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3824. Min Act: -0.0001

Data Index: 841302 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.4273. Min Range: -0.4273

Max Act: 0.3673. Min Act: -0.0001

Data Index: 1188211 (C4 (Web Text))

Max Activating Token Index: 494