Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 890 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.8973. Min Act: -0.1700

Data Index: 1558580 (Python Code)

Max Activating Token Index: 237

Text #1

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.8348. Min Act: -0.1700

Data Index: 1618452 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.7723. Min Act: -0.1700

Data Index: 1445419 (Python Code)

Max Activating Token Index: 461

Text #3

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.6473. Min Act: -0.1700

Data Index: 1650153 (Python Code)

Max Activating Token Index: 529

Text #4

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.6160. Min Act: -0.1700

Data Index: 1587085 (Python Code)

Max Activating Token Index: 211

Text #5

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.5848. Min Act: -0.1700

Data Index: 1634658 (Python Code)

Max Activating Token Index: 254

Text #6

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.5535. Min Act: -0.1700

Data Index: 1637514 (Python Code)

Max Activating Token Index: 296

Text #7

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.5535. Min Act: -0.1700

Data Index: 1525356 (Python Code)

Max Activating Token Index: 305

Text #8

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.5848. Min Act: -0.1700

Data Index: 1451942 (Python Code)

Max Activating Token Index: 464

Text #9

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.5223. Min Act: -0.1700

Data Index: 1508536 (Python Code)

Max Activating Token Index: 128

Text #10

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.4910. Min Act: -0.1700

Data Index: 1544630 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.4598. Min Act: -0.1700

Data Index: 1391489 (Python Code)

Max Activating Token Index: 366

Text #12

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.3973. Min Act: -0.1700

Data Index: 1485963 (Python Code)

Max Activating Token Index: 630

Text #13

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.2410. Min Act: -0.1700

Data Index: 1483912 (Python Code)

Max Activating Token Index: 694

Text #14

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.3660. Min Act: -0.1700

Data Index: 1647725 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.3035. Min Act: -0.1700

Data Index: 1640737 (Python Code)

Max Activating Token Index: 307

Text #16

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.3348. Min Act: -0.1700

Data Index: 1621287 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.3035. Min Act: -0.1700

Data Index: 1425965 (Python Code)

Max Activating Token Index: 426

Text #18

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.2723. Min Act: -0.1700

Data Index: 1436619 (Python Code)

Max Activating Token Index: 477

Text #19

Max Range: 5.8973. Min Range: -5.8973

Max Act: 5.2723. Min Act: -0.1700

Data Index: 1370974 (Python Code)

Max Activating Token Index: 474