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

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

Neuron 2970 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: 1.8999. Min Range: -1.8999

Max Act: 1.5246. Min Act: -0.0000

Data Index: 14988 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.8999. Min Act: -0.0000

Data Index: 527958 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.4843. Min Act: -0.0000

Data Index: 756987 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.4332. Min Act: -0.0000

Data Index: 845276 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.4167. Min Act: -0.0000

Data Index: 520522 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.3146. Min Act: -0.0000

Data Index: 208110 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.3806. Min Act: -0.0000

Data Index: 347397 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.2457. Min Act: -0.0000

Data Index: 514904 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.2512. Min Act: -0.0000

Data Index: 946050 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.1913. Min Act: -0.0000

Data Index: 555384 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.2269. Min Act: -0.0000

Data Index: 232576 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.2238. Min Act: -0.0000

Data Index: 821443 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.1163. Min Act: -0.0000

Data Index: 90002 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.2067. Min Act: -0.0000

Data Index: 936392 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.1950. Min Act: -0.0000

Data Index: 223314 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.0466. Min Act: -0.0000

Data Index: 243114 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.1658. Min Act: -0.0000

Data Index: 20508 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.1007. Min Act: -0.0000

Data Index: 181334 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.0818. Min Act: -0.0000

Data Index: 1022193 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 1.8999. Min Range: -1.8999

Max Act: 1.1097. Min Act: -0.0000

Data Index: 934389 (C4 (Web Text))

Max Activating Token Index: 230