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

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

Neuron 1330 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: 5.1086. Min Range: -5.1086

Max Act: 5.1071. Min Act: -0.0000

Data Index: 675978 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 5.1086. Min Range: -5.1086

Max Act: 4.9256. Min Act: -0.0000

Data Index: 1254498 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 5.1086. Min Range: -5.1086

Max Act: 5.1086. Min Act: -0.0000

Data Index: 1331375 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 5.1086. Min Range: -5.1086

Max Act: 4.3171. Min Act: -0.0000

Data Index: 114364 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 5.1086. Min Range: -5.1086

Max Act: 4.4297. Min Act: -0.0000

Data Index: 378465 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 5.1086. Min Range: -5.1086

Max Act: 4.1784. Min Act: -0.0000

Data Index: 263514 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 5.1086. Min Range: -5.1086

Max Act: 4.1839. Min Act: -0.0000

Data Index: 1083934 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 5.1086. Min Range: -5.1086

Max Act: 3.7928. Min Act: -0.0000

Data Index: 570984 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 5.1086. Min Range: -5.1086

Max Act: 3.7776. Min Act: -0.0000

Data Index: 1152503 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 5.1086. Min Range: -5.1086

Max Act: 4.0614. Min Act: -0.0000

Data Index: 908694 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 5.1086. Min Range: -5.1086

Max Act: 3.6839. Min Act: -0.0000

Data Index: 612181 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 5.1086. Min Range: -5.1086

Max Act: 3.6540. Min Act: -0.0000

Data Index: 7618 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 5.1086. Min Range: -5.1086

Max Act: 4.1182. Min Act: -0.0000

Data Index: 1302195 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 5.1086. Min Range: -5.1086

Max Act: 3.7533. Min Act: -0.0000

Data Index: 397648 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 5.1086. Min Range: -5.1086

Max Act: 4.2000. Min Act: -0.0000

Data Index: 84 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 5.1086. Min Range: -5.1086

Max Act: 3.5558. Min Act: -0.0000

Data Index: 1248852 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 5.1086. Min Range: -5.1086

Max Act: 3.5370. Min Act: -0.0000

Data Index: 831175 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 5.1086. Min Range: -5.1086

Max Act: 3.5427. Min Act: -0.0000

Data Index: 724080 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 5.1086. Min Range: -5.1086

Max Act: 3.7012. Min Act: -0.0000

Data Index: 490552 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 5.1086. Min Range: -5.1086

Max Act: 3.6655. Min Act: -0.0000

Data Index: 1616797 (Python Code)

Max Activating Token Index: 144