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

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

Neuron 1578 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.6274. Min Act: -0.0000

Data Index: 275038 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.5333. Min Act: -0.0000

Data Index: 200657 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.5036. Min Act: -0.0000

Data Index: 87946 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3914. Min Act: -0.0001

Data Index: 669126 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.4194. Min Act: -0.0001

Data Index: 1039033 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.4407. Min Act: -0.0001

Data Index: 547059 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.4292. Min Act: -0.0001

Data Index: 323461 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3335. Min Act: -0.0000

Data Index: 188113 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.5204. Min Act: -0.0000

Data Index: 841450 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1029447 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3775. Min Act: -0.0001

Data Index: 1016886 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.6308. Min Act: -0.0000

Data Index: 56809 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.3309. Min Act: -0.0000

Data Index: 927602 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.2455. Min Act: -0.0001

Data Index: 146251 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.2107. Min Act: -0.0000

Data Index: 711075 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1284156 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.1922. Min Act: -0.0001

Data Index: 316672 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.2955. Min Act: -0.0000

Data Index: 616980 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.2992. Min Act: -0.0000

Data Index: 72232 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 1.6308. Min Range: -1.6308

Max Act: 1.4129. Min Act: -0.0000

Data Index: 469825 (C4 (Web Text))

Max Activating Token Index: 686