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

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

Neuron 1364 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0300. Min Range: -2.0300

Max Act: 2.0300. Min Act: -0.0000

Data Index: 1644242 (Python Code)

Max Activating Token Index: 138

Text #1

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.7719. Min Act: -0.0000

Data Index: 1616403 (Python Code)

Max Activating Token Index: 337

Text #2

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.7435. Min Act: -0.0000

Data Index: 1596882 (Python Code)

Max Activating Token Index: 135

Text #3

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.7006. Min Act: -0.0000

Data Index: 1504769 (Python Code)

Max Activating Token Index: 614

Text #4

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.6897. Min Act: -0.0000

Data Index: 1446109 (Python Code)

Max Activating Token Index: 371

Text #5

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.6462. Min Act: -0.0000

Data Index: 1364393 (Python Code)

Max Activating Token Index: 609

Text #6

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.4871. Min Act: -0.0000

Data Index: 1602745 (Python Code)

Max Activating Token Index: 141

Text #7

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.4445. Min Act: -0.0000

Data Index: 1605774 (Python Code)

Max Activating Token Index: 783

Text #8

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1361588 (Python Code)

Max Activating Token Index: 646

Text #9

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.3279. Min Act: -0.0000

Data Index: 1643506 (Python Code)

Max Activating Token Index: 950

Text #10

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.4027. Min Act: -0.0000

Data Index: 1504939 (Python Code)

Max Activating Token Index: 34

Text #11

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.3993. Min Act: -0.0000

Data Index: 1432451 (Python Code)

Max Activating Token Index: 193

Text #12

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.4342. Min Act: -0.0000

Data Index: 1438818 (Python Code)

Max Activating Token Index: 935

Text #13

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1494565 (Python Code)

Max Activating Token Index: 537

Text #14

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.3375. Min Act: -0.0000

Data Index: 1388254 (Python Code)

Max Activating Token Index: 160

Text #15

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.2973. Min Act: -0.0000

Data Index: 1521580 (Python Code)

Max Activating Token Index: 93

Text #16

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.3347. Min Act: -0.0000

Data Index: 1494648 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1379169 (Python Code)

Max Activating Token Index: 836

Text #18

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.2543. Min Act: -0.0000

Data Index: 1372537 (Python Code)

Max Activating Token Index: 232

Text #19

Max Range: 2.0300. Min Range: -2.0300

Max Act: 1.3935. Min Act: -0.0000

Data Index: 1461841 (Python Code)

Max Activating Token Index: 875