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

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

Neuron 5574 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1231. Min Range: -6.1231

Max Act: 6.1231. Min Act: -0.0000

Data Index: 998257 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 6.1231. Min Range: -6.1231

Max Act: 5.9927. Min Act: -0.0000

Data Index: 1266845 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.9942. Min Act: -0.0000

Data Index: 1311665 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.6459. Min Act: -0.0000

Data Index: 197424 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.6039. Min Act: -0.0000

Data Index: 770252 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.5034. Min Act: -0.0000

Data Index: 1017167 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.3198. Min Act: -0.0000

Data Index: 1330007 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.4455. Min Act: -0.0000

Data Index: 852291 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.3269. Min Act: -0.0000

Data Index: 4689 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.3137. Min Act: -0.0000

Data Index: 528390 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.2588. Min Act: -0.0000

Data Index: 598441 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.0581. Min Act: -0.0000

Data Index: 54832 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.2284. Min Act: -0.0000

Data Index: 851957 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.2363. Min Act: -0.0000

Data Index: 511998 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.2186. Min Act: -0.0000

Data Index: 776527 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.1897. Min Act: -0.0000

Data Index: 297975 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.1703. Min Act: -0.0000

Data Index: 657924 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.1651. Min Act: -0.0000

Data Index: 826251 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 6.1231. Min Range: -6.1231

Max Act: 4.3078. Min Act: -0.0000

Data Index: 934072 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 6.1231. Min Range: -6.1231

Max Act: 3.9364. Min Act: -0.0000

Data Index: 1102321 (C4 (Web Text))

Max Activating Token Index: 82