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

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

Neuron 4671 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4531. Min Act: -0.0000

Data Index: 696423 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1325013 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1181604 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4296. Min Act: -0.0000

Data Index: 602559 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4366. Min Act: -0.0000

Data Index: 359068 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1349192 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4014. Min Act: -0.0000

Data Index: 109942 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4270. Min Act: -0.0000

Data Index: 423322 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4226. Min Act: -0.0000

Data Index: 30234 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4084. Min Act: -0.0000

Data Index: 491729 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4224. Min Act: -0.0000

Data Index: 967848 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.3921. Min Act: -0.0000

Data Index: 1100492 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4166. Min Act: -0.0000

Data Index: 424669 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.3993. Min Act: -0.0000

Data Index: 103817 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1109586 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.3992. Min Act: -0.0000

Data Index: 117877 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4157. Min Act: -0.0000

Data Index: 753724 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4010. Min Act: -0.0000

Data Index: 800058 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1106962 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.4591. Min Range: -0.4591

Max Act: 0.3956. Min Act: -0.0000

Data Index: 1221088 (C4 (Web Text))

Max Activating Token Index: 590