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

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

Neuron 1549 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1966. Min Range: -4.1966

Max Act: 4.1966. Min Act: -0.1700

Data Index: 868729 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 4.1966. Min Range: -4.1966

Max Act: 4.1654. Min Act: -0.1700

Data Index: 589714 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 4.1966. Min Range: -4.1966

Max Act: 4.1341. Min Act: -0.1700

Data Index: 309011 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 4.1966. Min Range: -4.1966

Max Act: 4.0403. Min Act: -0.1700

Data Index: 567778 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 4.1966. Min Range: -4.1966

Max Act: 4.0403. Min Act: -0.1700

Data Index: 410864 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 4.1966. Min Range: -4.1966

Max Act: 4.0716. Min Act: -0.1700

Data Index: 633641 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.9778. Min Act: -0.1700

Data Index: 231980 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.9778. Min Act: -0.1700

Data Index: 94061 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.9465. Min Act: -0.1700

Data Index: 197811 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 4.1966. Min Range: -4.1966

Max Act: 4.0403. Min Act: -0.1700

Data Index: 846647 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.9778. Min Act: -0.1700

Data Index: 668286 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 4.1966. Min Range: -4.1966

Max Act: 4.0091. Min Act: -0.1700

Data Index: 440240 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.9778. Min Act: -0.1700

Data Index: 206390 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 4.1966. Min Range: -4.1966

Max Act: 4.0091. Min Act: -0.1700

Data Index: 411375 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.9465. Min Act: -0.1700

Data Index: 684220 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.9778. Min Act: -0.1700

Data Index: 61492 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.9778. Min Act: -0.1700

Data Index: 281975 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.9465. Min Act: -0.1700

Data Index: 723871 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.9465. Min Act: -0.1700

Data Index: 440155 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 4.1966. Min Range: -4.1966

Max Act: 3.8527. Min Act: -0.1700

Data Index: 964545 (C4 (Web Text))

Max Activating Token Index: 911