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

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

Neuron 1354 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: 3.0152. Min Range: -3.0152

Max Act: 3.0152. Min Act: -0.1700

Data Index: 723607 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 3.0152. Min Range: -3.0152

Max Act: 3.0150. Min Act: -0.1700

Data Index: 1410653 (Python Code)

Max Activating Token Index: 819

Text #2

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9569. Min Act: -0.1700

Data Index: 39333 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9554. Min Act: -0.1700

Data Index: 1378976 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9293. Min Act: -0.1700

Data Index: 42055 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9212. Min Act: -0.1699

Data Index: 1433410 (Python Code)

Max Activating Token Index: 327

Text #6

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9138. Min Act: -0.1700

Data Index: 702927 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8848. Min Act: -0.1700

Data Index: 1541324 (Python Code)

Max Activating Token Index: 64

Text #8

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9040. Min Act: -0.1700

Data Index: 1563705 (Python Code)

Max Activating Token Index: 583

Text #9

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.9037. Min Act: -0.1700

Data Index: 934877 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8842. Min Act: -0.1686

Data Index: 623563 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8535. Min Act: -0.1700

Data Index: 786805 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8608. Min Act: -0.1700

Data Index: 67367 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8646. Min Act: -0.1700

Data Index: 635932 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8686. Min Act: -0.1700

Data Index: 788346 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8355. Min Act: -0.1700

Data Index: 1581713 (Python Code)

Max Activating Token Index: 467

Text #16

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8373. Min Act: -0.1700

Data Index: 10669 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8312. Min Act: -0.1700

Data Index: 1360461 (Python Code)

Max Activating Token Index: 931

Text #18

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8312. Min Act: -0.1700

Data Index: 1217130 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 3.0152. Min Range: -3.0152

Max Act: 2.8197. Min Act: -0.1700

Data Index: 185921 (C4 (Web Text))

Max Activating Token Index: 575