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

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

Neuron 1930 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: 0.9263. Min Range: -0.9263

Max Act: 0.9263. Min Act: -0.0001

Data Index: 128257 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7711. Min Act: -0.0001

Data Index: 1631605 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.8054. Min Act: -0.0001

Data Index: 123384 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7642. Min Act: -0.0001

Data Index: 1444286 (Python Code)

Max Activating Token Index: 193

Text #4

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7221. Min Act: -0.0001

Data Index: 1482660 (Python Code)

Max Activating Token Index: 96

Text #5

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7912. Min Act: -0.0001

Data Index: 1543332 (Python Code)

Max Activating Token Index: 223

Text #6

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7940. Min Act: -0.0001

Data Index: 1633288 (Python Code)

Max Activating Token Index: 406

Text #7

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6954. Min Act: -0.0001

Data Index: 1515160 (Python Code)

Max Activating Token Index: 175

Text #8

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.7010. Min Act: -0.0001

Data Index: 1397935 (Python Code)

Max Activating Token Index: 230

Text #9

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6712. Min Act: -0.0001

Data Index: 1583262 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6884. Min Act: -0.0001

Data Index: 1493373 (Python Code)

Max Activating Token Index: 382

Text #11

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6808. Min Act: -0.0001

Data Index: 1386262 (Python Code)

Max Activating Token Index: 315

Text #12

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6725. Min Act: -0.0001

Data Index: 1429693 (Python Code)

Max Activating Token Index: 926

Text #13

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6639. Min Act: -0.0001

Data Index: 1419974 (Python Code)

Max Activating Token Index: 105

Text #14

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6858. Min Act: -0.0001

Data Index: 1586341 (Python Code)

Max Activating Token Index: 762

Text #15

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6918. Min Act: -0.0001

Data Index: 1404494 (Python Code)

Max Activating Token Index: 107

Text #16

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6617. Min Act: -0.0001

Data Index: 1603325 (Python Code)

Max Activating Token Index: 57

Text #17

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6562. Min Act: -0.0001

Data Index: 1510870 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6520. Min Act: -0.0001

Data Index: 1560714 (Python Code)

Max Activating Token Index: 937

Text #19

Max Range: 0.9263. Min Range: -0.9263

Max Act: 0.6082. Min Act: -0.0001

Data Index: 1588293 (Python Code)

Max Activating Token Index: 47