Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2812 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 5.0207. Min Range: -5.0207

Max Act: 5.0207. Min Act: -0.1700

Data Index: 2316413 (Open Web Text)

Max Activating Token Index: 881

Text #1

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.8712. Min Act: -0.1700

Data Index: 7180176 (Open Web Text)

Max Activating Token Index: 838

Text #2

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.8375. Min Act: -0.1700

Data Index: 6203986 (Open Web Text)

Max Activating Token Index: 726

Text #3

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.8478. Min Act: -0.1700

Data Index: 3066309 (Open Web Text)

Max Activating Token Index: 916

Text #4

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7955. Min Act: -0.1700

Data Index: 5491601 (Open Web Text)

Max Activating Token Index: 117

Text #5

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7922. Min Act: -0.1700

Data Index: 510531 (Open Web Text)

Max Activating Token Index: 169

Text #6

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.8353. Min Act: -0.1700

Data Index: 4465390 (Open Web Text)

Max Activating Token Index: 544

Text #7

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7986. Min Act: -0.1700

Data Index: 5034177 (Open Web Text)

Max Activating Token Index: 35

Text #8

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7231. Min Act: -0.1700

Data Index: 4393659 (Open Web Text)

Max Activating Token Index: 526

Text #9

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7559. Min Act: -0.1700

Data Index: 4539186 (Open Web Text)

Max Activating Token Index: 790

Text #10

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7094. Min Act: -0.1700

Data Index: 4763496 (Open Web Text)

Max Activating Token Index: 183

Text #11

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7816. Min Act: -0.1700

Data Index: 3953313 (Open Web Text)

Max Activating Token Index: 480

Text #12

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7750. Min Act: -0.1700

Data Index: 6775328 (Open Web Text)

Max Activating Token Index: 396

Text #13

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7891. Min Act: -0.1700

Data Index: 4044987 (Open Web Text)

Max Activating Token Index: 91

Text #14

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7653. Min Act: -0.1700

Data Index: 382780 (Open Web Text)

Max Activating Token Index: 1007

Text #15

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7135. Min Act: -0.1700

Data Index: 8252254 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7261. Min Act: -0.1700

Data Index: 187104 (Open Web Text)

Max Activating Token Index: 739

Text #17

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7083. Min Act: -0.1700

Data Index: 6142927 (Open Web Text)

Max Activating Token Index: 269

Text #18

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.7607. Min Act: -0.1700

Data Index: 1985117 (Open Web Text)

Max Activating Token Index: 573

Text #19

Max Range: 5.0207. Min Range: -5.0207

Max Act: 4.6824. Min Act: -0.1700

Data Index: 693166 (Open Web Text)

Max Activating Token Index: 589