Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4759 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4367. Min Range: -3.4367

Max Act: 3.4367. Min Act: -0.0000

Data Index: 708087 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.9671. Min Act: -0.0000

Data Index: 1163598 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 3.4367. Min Range: -3.4367

Max Act: 2.1348. Min Act: -0.0000

Data Index: 373101 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.7042. Min Act: -0.0000

Data Index: 1115409 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.9482. Min Act: -0.0000

Data Index: 771808 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.6201. Min Act: -0.0000

Data Index: 581433 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.7989. Min Act: -0.0000

Data Index: 1323081 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.7036. Min Act: -0.0000

Data Index: 95156 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1077708 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1032392 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.3139. Min Act: -0.0000

Data Index: 957731 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.4695. Min Act: -0.0000

Data Index: 1308245 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.5099. Min Act: -0.0000

Data Index: 258410 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.4186. Min Act: -0.0000

Data Index: 875577 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.4395. Min Act: -0.0000

Data Index: 5303 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.1725. Min Act: -0.0000

Data Index: 76136 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.3543. Min Act: -0.0000

Data Index: 237071 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.3942. Min Act: -0.0000

Data Index: 1188367 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1088404 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 3.4367. Min Range: -3.4367

Max Act: 1.2754. Min Act: -0.0000

Data Index: 40487 (C4 (Web Text))

Max Activating Token Index: 944