Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 243 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.1244. Min Act: -0.1700

Data Index: 1632662 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.1086. Min Act: -0.1700

Data Index: 1230216 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0929. Min Act: -0.1700

Data Index: 541262 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0297. Min Act: -0.1700

Data Index: 1517552 (Python Code)

Max Activating Token Index: 623

Text #4

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0613. Min Act: -0.1700

Data Index: 1438428 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0613. Min Act: -0.1700

Data Index: 605895 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0455. Min Act: -0.1700

Data Index: 1038247 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0455. Min Act: -0.1700

Data Index: 1543276 (Python Code)

Max Activating Token Index: 909

Text #8

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0455. Min Act: -0.1700

Data Index: 1483150 (Python Code)

Max Activating Token Index: 548

Text #9

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0455. Min Act: -0.1700

Data Index: 1601591 (Python Code)

Max Activating Token Index: 464

Text #10

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0297. Min Act: -0.1700

Data Index: 1238689 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0455. Min Act: -0.1700

Data Index: 849580 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0613. Min Act: -0.1700

Data Index: 443139 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 3.1244. Min Range: -3.1244

Max Act: 2.9981. Min Act: -0.1700

Data Index: 1385053 (Python Code)

Max Activating Token Index: 959

Text #14

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0297. Min Act: -0.1700

Data Index: 1386512 (Python Code)

Max Activating Token Index: 803

Text #15

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0297. Min Act: -0.1700

Data Index: 1440614 (Python Code)

Max Activating Token Index: 108

Text #16

Max Range: 3.1244. Min Range: -3.1244

Max Act: 2.9981. Min Act: -0.1700

Data Index: 1467649 (Python Code)

Max Activating Token Index: 680

Text #17

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0297. Min Act: -0.1700

Data Index: 1487928 (Python Code)

Max Activating Token Index: 653

Text #18

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0297. Min Act: -0.1700

Data Index: 1451989 (Python Code)

Max Activating Token Index: 496

Text #19

Max Range: 3.1244. Min Range: -3.1244

Max Act: 3.0139. Min Act: -0.1700

Data Index: 1527545 (Python Code)

Max Activating Token Index: 775