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

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

Neuron 4505 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: 1.2699. Min Range: -1.2699

Max Act: 1.2699. Min Act: -0.0001

Data Index: 1509370 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 1.2699. Min Range: -1.2699

Max Act: 1.0540. Min Act: -0.0001

Data Index: 1399671 (Python Code)

Max Activating Token Index: 858

Text #2

Max Range: 1.2699. Min Range: -1.2699

Max Act: 1.1306. Min Act: -0.0001

Data Index: 1369428 (Python Code)

Max Activating Token Index: 469

Text #3

Max Range: 1.2699. Min Range: -1.2699

Max Act: 1.0113. Min Act: -0.0001

Data Index: 1401261 (Python Code)

Max Activating Token Index: 731

Text #4

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.8630. Min Act: -0.0001

Data Index: 1457085 (Python Code)

Max Activating Token Index: 996

Text #5

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.8090. Min Act: -0.0001

Data Index: 1386998 (Python Code)

Max Activating Token Index: 646

Text #6

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.8564. Min Act: -0.0001

Data Index: 1605442 (Python Code)

Max Activating Token Index: 139

Text #7

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.7972. Min Act: -0.0001

Data Index: 1548204 (Python Code)

Max Activating Token Index: 867

Text #8

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.8764. Min Act: -0.0001

Data Index: 1562465 (Python Code)

Max Activating Token Index: 867

Text #9

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.7890. Min Act: -0.0001

Data Index: 1509927 (Python Code)

Max Activating Token Index: 283

Text #10

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.8442. Min Act: -0.0001

Data Index: 1606613 (Python Code)

Max Activating Token Index: 335

Text #11

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.7540. Min Act: -0.0001

Data Index: 1596814 (Python Code)

Max Activating Token Index: 338

Text #12

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.7796. Min Act: -0.0001

Data Index: 1471718 (Python Code)

Max Activating Token Index: 721

Text #13

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.7279. Min Act: -0.0001

Data Index: 1563460 (Python Code)

Max Activating Token Index: 570

Text #14

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.7332. Min Act: -0.0001

Data Index: 1476777 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.7715. Min Act: -0.0001

Data Index: 1440880 (Python Code)

Max Activating Token Index: 153

Text #16

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.8372. Min Act: -0.0001

Data Index: 1470029 (Python Code)

Max Activating Token Index: 449

Text #17

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.7437. Min Act: -0.0001

Data Index: 1636751 (Python Code)

Max Activating Token Index: 38

Text #18

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.7447. Min Act: -0.0001

Data Index: 1419229 (Python Code)

Max Activating Token Index: 858

Text #19

Max Range: 1.2699. Min Range: -1.2699

Max Act: 0.7750. Min Act: -0.0001

Data Index: 1493115 (Python Code)

Max Activating Token Index: 855