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

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

Neuron 1857 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1960. Min Range: -5.1960

Max Act: 5.1960. Min Act: -0.1700

Data Index: 1465245 (Python Code)

Max Activating Token Index: 907

Text #1

Max Range: 5.1960. Min Range: -5.1960

Max Act: 5.0710. Min Act: -0.1700

Data Index: 1537985 (Python Code)

Max Activating Token Index: 136

Text #2

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.9772. Min Act: -0.1700

Data Index: 1430820 (Python Code)

Max Activating Token Index: 729

Text #3

Max Range: 5.1960. Min Range: -5.1960

Max Act: 5.0085. Min Act: -0.1700

Data Index: 1400860 (Python Code)

Max Activating Token Index: 307

Text #4

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.9772. Min Act: -0.1700

Data Index: 1411087 (Python Code)

Max Activating Token Index: 816

Text #5

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.8835. Min Act: -0.1700

Data Index: 1605004 (Python Code)

Max Activating Token Index: 970

Text #6

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.9147. Min Act: -0.1700

Data Index: 1437852 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.9772. Min Act: -0.1700

Data Index: 1643784 (Python Code)

Max Activating Token Index: 282

Text #8

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.8835. Min Act: -0.1700

Data Index: 1538372 (Python Code)

Max Activating Token Index: 865

Text #9

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.8835. Min Act: -0.1700

Data Index: 1421212 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.8522. Min Act: -0.1700

Data Index: 1534314 (Python Code)

Max Activating Token Index: 698

Text #11

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.8522. Min Act: -0.1700

Data Index: 1485935 (Python Code)

Max Activating Token Index: 561

Text #12

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.8835. Min Act: -0.1700

Data Index: 1427165 (Python Code)

Max Activating Token Index: 676

Text #13

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.8210. Min Act: -0.1700

Data Index: 1595204 (Python Code)

Max Activating Token Index: 874

Text #14

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.8522. Min Act: -0.1700

Data Index: 1641855 (Python Code)

Max Activating Token Index: 359

Text #15

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.8522. Min Act: -0.1700

Data Index: 1616340 (Python Code)

Max Activating Token Index: 974

Text #16

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.8210. Min Act: -0.1700

Data Index: 1535295 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.7272. Min Act: -0.1700

Data Index: 1503513 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.7272. Min Act: -0.1700

Data Index: 1560478 (Python Code)

Max Activating Token Index: 107

Text #19

Max Range: 5.1960. Min Range: -5.1960

Max Act: 4.7272. Min Act: -0.1700

Data Index: 1533240 (Python Code)

Max Activating Token Index: 444