Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 319 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.4221. Min Act: -0.1700

Data Index: 1501712 (Python Code)

Max Activating Token Index: 936

Text #1

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3805. Min Act: -0.1700

Data Index: 1620404 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3621. Min Act: -0.1700

Data Index: 1587715 (Python Code)

Max Activating Token Index: 355

Text #3

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3635. Min Act: -0.1700

Data Index: 1475129 (Python Code)

Max Activating Token Index: 646

Text #4

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3361. Min Act: -0.1700

Data Index: 1482426 (Python Code)

Max Activating Token Index: 590

Text #5

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3247. Min Act: -0.1700

Data Index: 1550359 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3227. Min Act: -0.1700

Data Index: 1538009 (Python Code)

Max Activating Token Index: 563

Text #7

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2775. Min Act: -0.1700

Data Index: 1581523 (Python Code)

Max Activating Token Index: 816

Text #8

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3003. Min Act: -0.1700

Data Index: 1539902 (Python Code)

Max Activating Token Index: 256

Text #9

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3030. Min Act: -0.1700

Data Index: 1620978 (Python Code)

Max Activating Token Index: 332

Text #10

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2741. Min Act: -0.1700

Data Index: 1433025 (Python Code)

Max Activating Token Index: 375

Text #11

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2532. Min Act: -0.1700

Data Index: 1461094 (Python Code)

Max Activating Token Index: 569

Text #12

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2713. Min Act: -0.1700

Data Index: 1633578 (Python Code)

Max Activating Token Index: 361

Text #13

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2510. Min Act: -0.1700

Data Index: 1649936 (Python Code)

Max Activating Token Index: 477

Text #14

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2593. Min Act: -0.1700

Data Index: 1655591 (Python Code)

Max Activating Token Index: 752

Text #15

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2260. Min Act: -0.1700

Data Index: 1616594 (Python Code)

Max Activating Token Index: 689

Text #16

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2229. Min Act: -0.1700

Data Index: 1504954 (Python Code)

Max Activating Token Index: 552

Text #17

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2191. Min Act: -0.1700

Data Index: 1565382 (Python Code)

Max Activating Token Index: 994

Text #18

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2384. Min Act: -0.1700

Data Index: 1496566 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2276. Min Act: -0.1700

Data Index: 1427171 (Python Code)

Max Activating Token Index: 299