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

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

Neuron 1379 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: 5.4597. Min Range: -5.4597

Max Act: 5.4597. Min Act: -0.1700

Data Index: 1638737 (Python Code)

Max Activating Token Index: 323

Text #1

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.4597. Min Act: -0.1700

Data Index: 136951 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.4284. Min Act: -0.1700

Data Index: 1430986 (Python Code)

Max Activating Token Index: 134

Text #3

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.4284. Min Act: -0.1700

Data Index: 1586552 (Python Code)

Max Activating Token Index: 252

Text #4

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.3972. Min Act: -0.1700

Data Index: 1378526 (Python Code)

Max Activating Token Index: 653

Text #5

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.3659. Min Act: -0.1700

Data Index: 1421303 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.3034. Min Act: -0.1700

Data Index: 1472470 (Python Code)

Max Activating Token Index: 184

Text #7

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.3347. Min Act: -0.1700

Data Index: 1409560 (Python Code)

Max Activating Token Index: 128

Text #8

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.3034. Min Act: -0.1700

Data Index: 1586808 (Python Code)

Max Activating Token Index: 431

Text #9

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.3034. Min Act: -0.1700

Data Index: 1477573 (Python Code)

Max Activating Token Index: 565

Text #10

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.2409. Min Act: -0.1700

Data Index: 1488796 (Python Code)

Max Activating Token Index: 81

Text #11

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.3034. Min Act: -0.1700

Data Index: 1612230 (Python Code)

Max Activating Token Index: 395

Text #12

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.1784. Min Act: -0.1700

Data Index: 419364 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.2097. Min Act: -0.1700

Data Index: 1488223 (Python Code)

Max Activating Token Index: 419

Text #14

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.1784. Min Act: -0.1700

Data Index: 1393811 (Python Code)

Max Activating Token Index: 547

Text #15

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.2409. Min Act: -0.1700

Data Index: 1600572 (Python Code)

Max Activating Token Index: 395

Text #16

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.2097. Min Act: -0.1700

Data Index: 1459420 (Python Code)

Max Activating Token Index: 199

Text #17

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.2409. Min Act: -0.1700

Data Index: 1458477 (Python Code)

Max Activating Token Index: 452

Text #18

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.3034. Min Act: -0.1700

Data Index: 1516379 (Python Code)

Max Activating Token Index: 325

Text #19

Max Range: 5.4597. Min Range: -5.4597

Max Act: 5.2097. Min Act: -0.1700

Data Index: 1593511 (Python Code)

Max Activating Token Index: 217