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

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

Neuron 1329 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8476. Min Act: -0.0001

Data Index: 1575391 (Python Code)

Max Activating Token Index: 98

Text #1

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8082. Min Act: -0.0001

Data Index: 1656027 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8154. Min Act: -0.0001

Data Index: 1641586 (Python Code)

Max Activating Token Index: 579

Text #3

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8688. Min Act: -0.0001

Data Index: 1379381 (Python Code)

Max Activating Token Index: 383

Text #4

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7494. Min Act: -0.0001

Data Index: 1370054 (Python Code)

Max Activating Token Index: 469

Text #5

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7626. Min Act: -0.0001

Data Index: 1589172 (Python Code)

Max Activating Token Index: 438

Text #6

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7709. Min Act: -0.0001

Data Index: 1451739 (Python Code)

Max Activating Token Index: 156

Text #7

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7895. Min Act: -0.0001

Data Index: 1620437 (Python Code)

Max Activating Token Index: 453

Text #8

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8991. Min Act: -0.0001

Data Index: 1400417 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6587. Min Act: -0.0001

Data Index: 1540424 (Python Code)

Max Activating Token Index: 398

Text #10

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7448. Min Act: -0.0001

Data Index: 1427190 (Python Code)

Max Activating Token Index: 206

Text #11

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8375. Min Act: -0.0001

Data Index: 1435510 (Python Code)

Max Activating Token Index: 171

Text #12

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7170. Min Act: -0.0001

Data Index: 1448160 (Python Code)

Max Activating Token Index: 94

Text #13

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7386. Min Act: -0.0001

Data Index: 1387606 (Python Code)

Max Activating Token Index: 123

Text #14

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7823. Min Act: -0.0001

Data Index: 1398074 (Python Code)

Max Activating Token Index: 86

Text #15

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6881. Min Act: -0.0001

Data Index: 1365058 (Python Code)

Max Activating Token Index: 210

Text #16

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1401648 (Python Code)

Max Activating Token Index: 81

Text #17

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6997. Min Act: -0.0001

Data Index: 1558387 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7959. Min Act: -0.0001

Data Index: 1643041 (Python Code)

Max Activating Token Index: 254

Text #19

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7179. Min Act: -0.0001

Data Index: 1456549 (Python Code)

Max Activating Token Index: 151