Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 458 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.2062. Min Act: -0.1700

Data Index: 1138323 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1590. Min Act: -0.1700

Data Index: 893558 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1747. Min Act: -0.1700

Data Index: 1051165 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1432. Min Act: -0.1700

Data Index: 1078969 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1590. Min Act: -0.1700

Data Index: 201172 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1590. Min Act: -0.1700

Data Index: 753936 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1275. Min Act: -0.1700

Data Index: 79242 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1275. Min Act: -0.1700

Data Index: 263618 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1275. Min Act: -0.1700

Data Index: 1005309 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1117. Min Act: -0.1700

Data Index: 511056 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1275. Min Act: -0.1700

Data Index: 1062420 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1117. Min Act: -0.1700

Data Index: 717572 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1275. Min Act: -0.1700

Data Index: 1028059 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1117. Min Act: -0.1700

Data Index: 336401 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.0959. Min Act: -0.1700

Data Index: 812500 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.0802. Min Act: -0.1700

Data Index: 164659 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.1117. Min Act: -0.1700

Data Index: 574370 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.0959. Min Act: -0.1700

Data Index: 1340898 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.0802. Min Act: -0.1700

Data Index: 996472 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 3.2062. Min Range: -3.2062

Max Act: 3.0644. Min Act: -0.1700

Data Index: 982798 (C4 (Web Text))

Max Activating Token Index: 881