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

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

Neuron 1758 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3946. Min Act: -0.0001

Data Index: 1381240 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.4043. Min Act: -0.0001

Data Index: 1563978 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3960. Min Act: -0.0001

Data Index: 1535861 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3864. Min Act: -0.0001

Data Index: 1554098 (Python Code)

Max Activating Token Index: 20

Text #4

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3793. Min Act: -0.0001

Data Index: 1583419 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3232. Min Act: -0.0002

Data Index: 722476 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3445. Min Act: -0.0001

Data Index: 1589644 (Python Code)

Max Activating Token Index: 13

Text #7

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3576. Min Act: -0.0001

Data Index: 1560024 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3775. Min Act: -0.0001

Data Index: 1448611 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3442. Min Act: -0.0001

Data Index: 1503913 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3296. Min Act: -0.0001

Data Index: 1371547 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3559. Min Act: -0.0001

Data Index: 1427407 (Python Code)

Max Activating Token Index: 4

Text #12

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3503. Min Act: -0.0001

Data Index: 1656595 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3454. Min Act: -0.0001

Data Index: 1431270 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3301. Min Act: -0.0001

Data Index: 1378383 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3324. Min Act: -0.0001

Data Index: 1529624 (Python Code)

Max Activating Token Index: 182

Text #16

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3256. Min Act: -0.0001

Data Index: 1375469 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3362. Min Act: -0.0001

Data Index: 1454992 (Python Code)

Max Activating Token Index: 964

Text #18

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3385. Min Act: -0.0001

Data Index: 1475898 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.4043. Min Range: -0.4043

Max Act: 0.3261. Min Act: -0.0001

Data Index: 1376792 (Python Code)

Max Activating Token Index: 12