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

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

Neuron 4136 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4111. Min Range: -2.4111

Max Act: 2.4111. Min Act: -0.0000

Data Index: 1472816 (Python Code)

Max Activating Token Index: 114

Text #1

Max Range: 2.4111. Min Range: -2.4111

Max Act: 2.0009. Min Act: -0.0000

Data Index: 1426089 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.8653. Min Act: -0.0000

Data Index: 1450991 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 2.4111. Min Range: -2.4111

Max Act: 2.0212. Min Act: -0.0000

Data Index: 1406474 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 2.4111. Min Range: -2.4111

Max Act: 2.0198. Min Act: -0.0000

Data Index: 1471129 (Python Code)

Max Activating Token Index: 899

Text #5

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.8108. Min Act: -0.0000

Data Index: 1393640 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.6622. Min Act: -0.0000

Data Index: 1397126 (Python Code)

Max Activating Token Index: 436

Text #7

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.5985. Min Act: -0.0000

Data Index: 1593990 (Python Code)

Max Activating Token Index: 434

Text #8

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.7002. Min Act: -0.0001

Data Index: 1383395 (Python Code)

Max Activating Token Index: 796

Text #9

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.8713. Min Act: -0.0000

Data Index: 1502978 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.7340. Min Act: -0.0001

Data Index: 1410557 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.8312. Min Act: -0.0000

Data Index: 1394531 (Python Code)

Max Activating Token Index: 190

Text #12

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.8337. Min Act: -0.0000

Data Index: 1436257 (Python Code)

Max Activating Token Index: 183

Text #13

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.6835. Min Act: -0.0000

Data Index: 1473916 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.6526. Min Act: -0.0000

Data Index: 1478242 (Python Code)

Max Activating Token Index: 958

Text #15

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.7531. Min Act: -0.0001

Data Index: 1544838 (Python Code)

Max Activating Token Index: 770

Text #16

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.4950. Min Act: -0.0000

Data Index: 1615753 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.6744. Min Act: -0.0001

Data Index: 1385660 (Python Code)

Max Activating Token Index: 646

Text #18

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.5868. Min Act: -0.0000

Data Index: 1392837 (Python Code)

Max Activating Token Index: 181

Text #19

Max Range: 2.4111. Min Range: -2.4111

Max Act: 1.6082. Min Act: -0.0001

Data Index: 1551350 (Python Code)

Max Activating Token Index: 818