Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3718 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2909. Min Act: -0.0002

Data Index: 709031 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2771. Min Act: -0.0002

Data Index: 1203883 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.3129. Min Act: -0.0002

Data Index: 1093274 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2795. Min Act: -0.0002

Data Index: 966500 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2609. Min Act: -0.0002

Data Index: 386036 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2645. Min Act: -0.0002

Data Index: 408478 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2658. Min Act: -0.0002

Data Index: 173787 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2339. Min Act: -0.0002

Data Index: 1210036 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2468. Min Act: -0.0002

Data Index: 1199024 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2449. Min Act: -0.0002

Data Index: 758309 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2298. Min Act: -0.0002

Data Index: 179180 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2816. Min Act: -0.0002

Data Index: 870556 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2447. Min Act: -0.0002

Data Index: 1342214 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2234. Min Act: -0.0002

Data Index: 678257 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2346. Min Act: -0.0002

Data Index: 1247598 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2559. Min Act: -0.0002

Data Index: 83222 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2214. Min Act: -0.0002

Data Index: 916000 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2549. Min Act: -0.0002

Data Index: 962120 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2489. Min Act: -0.0002

Data Index: 1159007 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.3129. Min Range: -0.3129

Max Act: 0.2783. Min Act: -0.0002

Data Index: 369339 (C4 (Web Text))

Max Activating Token Index: 687