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

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

Neuron 1805 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6414. Min Range: -8.6414

Max Act: 8.5238. Min Act: -0.0000

Data Index: 1347860 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 8.6414. Min Range: -8.6414

Max Act: 8.6414. Min Act: -0.0000

Data Index: 1115449 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 8.6414. Min Range: -8.6414

Max Act: 8.2557. Min Act: -0.0000

Data Index: 1155085 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 8.6414. Min Range: -8.6414

Max Act: 8.0037. Min Act: -0.0000

Data Index: 77539 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 8.6414. Min Range: -8.6414

Max Act: 8.0981. Min Act: -0.0000

Data Index: 242169 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 8.6414. Min Range: -8.6414

Max Act: 8.0165. Min Act: -0.0000

Data Index: 947726 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 8.6414. Min Range: -8.6414

Max Act: 7.6161. Min Act: -0.0000

Data Index: 37711 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 8.6414. Min Range: -8.6414

Max Act: 7.6677. Min Act: -0.0000

Data Index: 472472 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 8.6414. Min Range: -8.6414

Max Act: 7.6811. Min Act: -0.0000

Data Index: 8177 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 8.6414. Min Range: -8.6414

Max Act: 7.5585. Min Act: -0.0000

Data Index: 718611 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 8.6414. Min Range: -8.6414

Max Act: 7.5011. Min Act: -0.0000

Data Index: 945230 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 8.6414. Min Range: -8.6414

Max Act: 7.3854. Min Act: -0.0000

Data Index: 1191747 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 8.6414. Min Range: -8.6414

Max Act: 7.3002. Min Act: -0.0000

Data Index: 274761 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 8.6414. Min Range: -8.6414

Max Act: 6.9648. Min Act: -0.0000

Data Index: 334925 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 8.6414. Min Range: -8.6414

Max Act: 6.7658. Min Act: -0.0000

Data Index: 821612 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 8.6414. Min Range: -8.6414

Max Act: 6.6905. Min Act: -0.0000

Data Index: 1054784 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 8.6414. Min Range: -8.6414

Max Act: 6.7159. Min Act: -0.0000

Data Index: 280978 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 8.6414. Min Range: -8.6414

Max Act: 7.0574. Min Act: -0.0000

Data Index: 893266 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 8.6414. Min Range: -8.6414

Max Act: 6.4779. Min Act: -0.0000

Data Index: 803962 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 8.6414. Min Range: -8.6414

Max Act: 7.0164. Min Act: -0.0000

Data Index: 29181 (C4 (Web Text))

Max Activating Token Index: 281