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

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

Neuron 5258 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: 4.0189. Min Range: -4.0189

Max Act: 4.0189. Min Act: -0.0000

Data Index: 794947 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 4.0189. Min Range: -4.0189

Max Act: 4.0050. Min Act: -0.0000

Data Index: 968431 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 4.0189. Min Range: -4.0189

Max Act: 3.8484. Min Act: -0.0000

Data Index: 1046654 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 4.0189. Min Range: -4.0189

Max Act: 3.9113. Min Act: -0.0000

Data Index: 1082371 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 4.0189. Min Range: -4.0189

Max Act: 3.5925. Min Act: -0.0000

Data Index: 327848 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 4.0189. Min Range: -4.0189

Max Act: 3.3310. Min Act: -0.0000

Data Index: 471198 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 4.0189. Min Range: -4.0189

Max Act: 3.1434. Min Act: -0.0000

Data Index: 1353165 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 4.0189. Min Range: -4.0189

Max Act: 2.9719. Min Act: -0.0000

Data Index: 991907 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 4.0189. Min Range: -4.0189

Max Act: 3.3973. Min Act: -0.0000

Data Index: 348678 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 4.0189. Min Range: -4.0189

Max Act: 2.7412. Min Act: -0.0000

Data Index: 643792 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 4.0189. Min Range: -4.0189

Max Act: 3.3145. Min Act: -0.0000

Data Index: 665266 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 4.0189. Min Range: -4.0189

Max Act: 2.9174. Min Act: -0.0000

Data Index: 1193806 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 4.0189. Min Range: -4.0189

Max Act: 3.1810. Min Act: -0.0000

Data Index: 561400 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 4.0189. Min Range: -4.0189

Max Act: 3.0288. Min Act: -0.0000

Data Index: 202545 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 4.0189. Min Range: -4.0189

Max Act: 2.9890. Min Act: -0.0000

Data Index: 481835 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 4.0189. Min Range: -4.0189

Max Act: 2.6490. Min Act: -0.0000

Data Index: 888087 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 4.0189. Min Range: -4.0189

Max Act: 2.7716. Min Act: -0.0000

Data Index: 656927 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 4.0189. Min Range: -4.0189

Max Act: 2.7781. Min Act: -0.0000

Data Index: 272216 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 4.0189. Min Range: -4.0189

Max Act: 2.9015. Min Act: -0.0000

Data Index: 845236 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 4.0189. Min Range: -4.0189

Max Act: 2.7464. Min Act: -0.0000

Data Index: 225878 (C4 (Web Text))

Max Activating Token Index: 542