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

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

Neuron 1507 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: 3.5555. Min Range: -3.5555

Max Act: 3.5555. Min Act: -0.1700

Data Index: 1314830 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4928. Min Act: -0.1700

Data Index: 1087143 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4458. Min Act: -0.1700

Data Index: 791955 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4301. Min Act: -0.1700

Data Index: 544124 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.4144. Min Act: -0.1700

Data Index: 735525 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.3674. Min Act: -0.1700

Data Index: 1073126 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.3046. Min Act: -0.1700

Data Index: 237147 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.2889. Min Act: -0.1700

Data Index: 1483389 (Python Code)

Max Activating Token Index: 986

Text #8

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.3046. Min Act: -0.1700

Data Index: 1618738 (Python Code)

Max Activating Token Index: 674

Text #9

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.2417. Min Act: -0.1700

Data Index: 637835 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.2417. Min Act: -0.1700

Data Index: 1478485 (Python Code)

Max Activating Token Index: 743

Text #11

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.2103. Min Act: -0.1699

Data Index: 930697 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.2260. Min Act: -0.1700

Data Index: 387438 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.2103. Min Act: -0.1700

Data Index: 681976 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.2103. Min Act: -0.1700

Data Index: 1225151 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.1946. Min Act: -0.1700

Data Index: 1174043 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.1946. Min Act: -0.1700

Data Index: 1034155 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.1631. Min Act: -0.1700

Data Index: 16585 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.1631. Min Act: -0.1700

Data Index: 960346 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 3.5555. Min Range: -3.5555

Max Act: 3.1631. Min Act: -0.1700

Data Index: 933644 (C4 (Web Text))

Max Activating Token Index: 304