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

Dataset: Open Web Text

Neuron 927 in Layer 4

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: 4.8011. Min Range: -4.8011

Max Act: 4.8011. Min Act: -0.1700

Data Index: 2752042 (Open Web Text)

Max Activating Token Index: 839

Text #1

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.7130. Min Act: -0.1700

Data Index: 538215 (Open Web Text)

Max Activating Token Index: 88

Text #2

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.6944. Min Act: -0.1700

Data Index: 4798351 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.7081. Min Act: -0.1700

Data Index: 3516829 (Open Web Text)

Max Activating Token Index: 898

Text #4

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.6183. Min Act: -0.1700

Data Index: 1091948 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.5263. Min Act: -0.1700

Data Index: 7272272 (Open Web Text)

Max Activating Token Index: 923

Text #6

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.5589. Min Act: -0.1700

Data Index: 6564109 (Open Web Text)

Max Activating Token Index: 575

Text #7

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.5132. Min Act: -0.1700

Data Index: 2424871 (Open Web Text)

Max Activating Token Index: 795

Text #8

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.4539. Min Act: -0.1700

Data Index: 5675416 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.3778. Min Act: -0.1700

Data Index: 8154046 (Open Web Text)

Max Activating Token Index: 786

Text #10

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.4457. Min Act: -0.1700

Data Index: 4637311 (Open Web Text)

Max Activating Token Index: 587

Text #11

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.3849. Min Act: -0.1700

Data Index: 7134799 (Open Web Text)

Max Activating Token Index: 416

Text #12

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.4148. Min Act: -0.1700

Data Index: 4012318 (Open Web Text)

Max Activating Token Index: 614

Text #13

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.3914. Min Act: -0.1700

Data Index: 206927 (Open Web Text)

Max Activating Token Index: 243

Text #14

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.3842. Min Act: -0.1700

Data Index: 8035012 (Open Web Text)

Max Activating Token Index: 327

Text #15

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.4161. Min Act: -0.1700

Data Index: 6729113 (Open Web Text)

Max Activating Token Index: 698

Text #16

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.4201. Min Act: -0.1700

Data Index: 7965138 (Open Web Text)

Max Activating Token Index: 456

Text #17

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.3881. Min Act: -0.1700

Data Index: 954809 (Open Web Text)

Max Activating Token Index: 77

Text #18

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.3620. Min Act: -0.1700

Data Index: 1343948 (Open Web Text)

Max Activating Token Index: 526

Text #19

Max Range: 4.8011. Min Range: -4.8011

Max Act: 4.3640. Min Act: -0.1700

Data Index: 1654174 (Open Web Text)

Max Activating Token Index: 2