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

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

Neuron 2923 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1980. Min Range: -5.1980

Max Act: 5.1980. Min Act: -0.0000

Data Index: 1129701 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 5.1980. Min Range: -5.1980

Max Act: 5.1185. Min Act: -0.0001

Data Index: 196843 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.9813. Min Act: -0.0000

Data Index: 612951 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 5.1980. Min Range: -5.1980

Max Act: 5.1575. Min Act: -0.0001

Data Index: 524242 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.7938. Min Act: -0.0000

Data Index: 1342218 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.9338. Min Act: -0.0000

Data Index: 1327311 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.5634. Min Act: -0.0000

Data Index: 513397 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.6167. Min Act: -0.0000

Data Index: 682078 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.5283. Min Act: -0.0000

Data Index: 535485 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.3821. Min Act: -0.0001

Data Index: 192178 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.6613. Min Act: -0.0001

Data Index: 224148 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.9535. Min Act: -0.0000

Data Index: 753081 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.6136. Min Act: -0.0000

Data Index: 606972 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.8200. Min Act: -0.0000

Data Index: 1145599 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.7744. Min Act: -0.0000

Data Index: 169688 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.3389. Min Act: -0.0000

Data Index: 884188 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.1377. Min Act: -0.0000

Data Index: 264739 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 5.1980. Min Range: -5.1980

Max Act: 3.9284. Min Act: -0.0000

Data Index: 618621 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.0571. Min Act: -0.0000

Data Index: 1102297 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 5.1980. Min Range: -5.1980

Max Act: 4.5551. Min Act: -0.0000

Data Index: 745071 (C4 (Web Text))

Max Activating Token Index: 393