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

Dataset: Open Web Text

Neuron 1940 in Layer 3

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: 3.4046. Min Range: -3.4046

Max Act: 3.4046. Min Act: -0.1700

Data Index: 4400998 (Open Web Text)

Max Activating Token Index: 321

Text #1

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.4019. Min Act: -0.1700

Data Index: 7526449 (Open Web Text)

Max Activating Token Index: 521

Text #2

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3408. Min Act: -0.1700

Data Index: 4164920 (Open Web Text)

Max Activating Token Index: 564

Text #3

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3739. Min Act: -0.1700

Data Index: 3060752 (Open Web Text)

Max Activating Token Index: 661

Text #4

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3153. Min Act: -0.1700

Data Index: 1772424 (Open Web Text)

Max Activating Token Index: 792

Text #5

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3619. Min Act: -0.1700

Data Index: 1851997 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3210. Min Act: -0.1700

Data Index: 6197797 (Open Web Text)

Max Activating Token Index: 439

Text #7

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3394. Min Act: -0.1700

Data Index: 8467327 (Open Web Text)

Max Activating Token Index: 769

Text #8

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3013. Min Act: -0.1700

Data Index: 2768911 (Open Web Text)

Max Activating Token Index: 465

Text #9

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3207. Min Act: -0.1700

Data Index: 2676296 (Open Web Text)

Max Activating Token Index: 701

Text #10

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3045. Min Act: -0.1700

Data Index: 8023595 (Open Web Text)

Max Activating Token Index: 549

Text #11

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2675. Min Act: -0.1700

Data Index: 4013851 (Open Web Text)

Max Activating Token Index: 700

Text #12

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.3072. Min Act: -0.1700

Data Index: 2908219 (Open Web Text)

Max Activating Token Index: 728

Text #13

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2989. Min Act: -0.1700

Data Index: 5748010 (Open Web Text)

Max Activating Token Index: 970

Text #14

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2757. Min Act: -0.1700

Data Index: 8011040 (Open Web Text)

Max Activating Token Index: 119

Text #15

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2714. Min Act: -0.1700

Data Index: 8665220 (Open Web Text)

Max Activating Token Index: 132

Text #16

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2976. Min Act: -0.1700

Data Index: 2275805 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2717. Min Act: -0.1700

Data Index: 2139293 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2678. Min Act: -0.1700

Data Index: 4724029 (Open Web Text)

Max Activating Token Index: 194

Text #19

Max Range: 3.4046. Min Range: -3.4046

Max Act: 3.2547. Min Act: -0.1700

Data Index: 1627502 (Open Web Text)

Max Activating Token Index: 758