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

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

Neuron 1191 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.5320. Min Act: -0.0000

Data Index: 822417 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 3.5320. Min Range: -3.5320

Max Act: 3.2348. Min Act: -0.0000

Data Index: 28499 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.6377. Min Act: -0.0000

Data Index: 853324 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.5025. Min Act: -0.0000

Data Index: 897601 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.3911. Min Act: -0.0000

Data Index: 1214476 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.2269. Min Act: -0.0000

Data Index: 9892 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.3113. Min Act: -0.0000

Data Index: 376276 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.1717. Min Act: -0.0000

Data Index: 97468 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.2708. Min Act: -0.0000

Data Index: 483105 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.3965. Min Act: -0.0000

Data Index: 301358 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.0137. Min Act: -0.0000

Data Index: 25325 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.2601. Min Act: -0.0000

Data Index: 247301 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.1369. Min Act: -0.0000

Data Index: 658011 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.0860. Min Act: -0.0000

Data Index: 781115 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.0203. Min Act: -0.0000

Data Index: 294755 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.0157. Min Act: -0.0000

Data Index: 972141 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 3.5320. Min Range: -3.5320

Max Act: 1.8975. Min Act: -0.0000

Data Index: 100804 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 3.5320. Min Range: -3.5320

Max Act: 1.8916. Min Act: -0.0000

Data Index: 43084 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.1039. Min Act: -0.0000

Data Index: 575466 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 3.5320. Min Range: -3.5320

Max Act: 2.0987. Min Act: -0.0000

Data Index: 1342027 (C4 (Web Text))

Max Activating Token Index: 863