Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2991 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.5225. Min Act: -0.0001

Data Index: 1542833 (Python Code)

Max Activating Token Index: 87

Text #1

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.3929. Min Act: -0.0001

Data Index: 1583214 (Python Code)

Max Activating Token Index: 287

Text #2

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.2981. Min Act: -0.0001

Data Index: 1095077 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.2179. Min Act: -0.0001

Data Index: 1236731 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.2209. Min Act: -0.0001

Data Index: 1488045 (Python Code)

Max Activating Token Index: 502

Text #5

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.2250. Min Act: -0.0000

Data Index: 303169 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.2300. Min Act: -0.0001

Data Index: 758082 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.2057. Min Act: -0.0001

Data Index: 1364189 (Python Code)

Max Activating Token Index: 356

Text #8

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.1312. Min Act: -0.0001

Data Index: 1261600 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.1331. Min Act: -0.0001

Data Index: 1537027 (Python Code)

Max Activating Token Index: 566

Text #10

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0556. Min Act: -0.0000

Data Index: 1506910 (Python Code)

Max Activating Token Index: 775

Text #11

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0739. Min Act: -0.0001

Data Index: 691009 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.5225. Min Range: -1.5225

Max Act: 0.8919. Min Act: -0.0001

Data Index: 423931 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0633. Min Act: -0.0001

Data Index: 1370921 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0328. Min Act: -0.0001

Data Index: 1449817 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0395. Min Act: -0.0001

Data Index: 1421801 (Python Code)

Max Activating Token Index: 449

Text #16

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0200. Min Act: -0.0001

Data Index: 1599912 (Python Code)

Max Activating Token Index: 689

Text #17

Max Range: 1.5225. Min Range: -1.5225

Max Act: 0.9729. Min Act: -0.0000

Data Index: 949092 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 1.5225. Min Range: -1.5225

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1306910 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 1.5225. Min Range: -1.5225

Max Act: 0.9666. Min Act: -0.0001

Data Index: 1417584 (Python Code)

Max Activating Token Index: 58