Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 138 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.8288. Min Act: -0.0003

Data Index: 1585900 (Python Code)

Max Activating Token Index: 707

Text #1

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.3179. Min Act: -0.0003

Data Index: 1601068 (Python Code)

Max Activating Token Index: 942

Text #2

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.3064. Min Act: -0.0003

Data Index: 1414414 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2907. Min Act: -0.0003

Data Index: 1405776 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2882. Min Act: -0.0003

Data Index: 1565610 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2850. Min Act: -0.0003

Data Index: 1368887 (Python Code)

Max Activating Token Index: 467

Text #6

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2299. Min Act: -0.0003

Data Index: 1542559 (Python Code)

Max Activating Token Index: 313

Text #7

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2864. Min Act: -0.0003

Data Index: 1362448 (Python Code)

Max Activating Token Index: 721

Text #8

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2439. Min Act: -0.0003

Data Index: 1619582 (Python Code)

Max Activating Token Index: 832

Text #9

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2702. Min Act: -0.0003

Data Index: 1399832 (Python Code)

Max Activating Token Index: 921

Text #10

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2250. Min Act: -0.0003

Data Index: 1455337 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2578. Min Act: -0.0003

Data Index: 1417522 (Python Code)

Max Activating Token Index: 465

Text #12

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2364. Min Act: -0.0003

Data Index: 1605670 (Python Code)

Max Activating Token Index: 574

Text #13

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2239. Min Act: -0.0003

Data Index: 1570184 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2375. Min Act: -0.0003

Data Index: 1370190 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2198. Min Act: -0.0003

Data Index: 1477401 (Python Code)

Max Activating Token Index: 311

Text #16

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2146. Min Act: -0.0003

Data Index: 1642725 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2144. Min Act: -0.0003

Data Index: 1379282 (Python Code)

Max Activating Token Index: 668

Text #18

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.2275. Min Act: -0.0003

Data Index: 1514090 (Python Code)

Max Activating Token Index: 75

Text #19

Max Range: 0.8288. Min Range: -0.8288

Max Act: 0.1619. Min Act: -0.0003

Data Index: 1559235 (Python Code)

Max Activating Token Index: 290