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

Dataset: Open Web Text

Neuron 919 in Layer 1

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: 4.2561. Min Range: -4.2561

Max Act: 4.2561. Min Act: -0.1700

Data Index: 8029025 (Open Web Text)

Max Activating Token Index: 619

Text #1

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.2147. Min Act: -0.1700

Data Index: 8690006 (Open Web Text)

Max Activating Token Index: 858

Text #2

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.1515. Min Act: -0.1700

Data Index: 3568953 (Open Web Text)

Max Activating Token Index: 861

Text #3

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.1413. Min Act: -0.1700

Data Index: 8610311 (Open Web Text)

Max Activating Token Index: 554

Text #4

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.1479. Min Act: -0.1700

Data Index: 5246317 (Open Web Text)

Max Activating Token Index: 218

Text #5

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.1416. Min Act: -0.1700

Data Index: 6566402 (Open Web Text)

Max Activating Token Index: 876

Text #6

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.1148. Min Act: -0.1700

Data Index: 988952 (Open Web Text)

Max Activating Token Index: 240

Text #7

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0946. Min Act: -0.1700

Data Index: 4287140 (Open Web Text)

Max Activating Token Index: 616

Text #8

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.1358. Min Act: -0.1700

Data Index: 5197782 (Open Web Text)

Max Activating Token Index: 234

Text #9

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0949. Min Act: -0.1700

Data Index: 7019076 (Open Web Text)

Max Activating Token Index: 91

Text #10

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0867. Min Act: -0.1700

Data Index: 8816846 (Open Web Text)

Max Activating Token Index: 118

Text #11

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0828. Min Act: -0.1700

Data Index: 4617371 (Open Web Text)

Max Activating Token Index: 769

Text #12

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0857. Min Act: -0.1700

Data Index: 8291696 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0717. Min Act: -0.1700

Data Index: 5489082 (Open Web Text)

Max Activating Token Index: 196

Text #14

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0903. Min Act: -0.1700

Data Index: 533302 (Open Web Text)

Max Activating Token Index: 647

Text #15

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0878. Min Act: -0.1700

Data Index: 22830 (Open Web Text)

Max Activating Token Index: 788

Text #16

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0920. Min Act: -0.1700

Data Index: 834850 (Open Web Text)

Max Activating Token Index: 505

Text #17

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0802. Min Act: -0.1700

Data Index: 1071158 (Open Web Text)

Max Activating Token Index: 304

Text #18

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0593. Min Act: -0.1700

Data Index: 3210394 (Open Web Text)

Max Activating Token Index: 326

Text #19

Max Range: 4.2561. Min Range: -4.2561

Max Act: 4.0644. Min Act: -0.1700

Data Index: 3399168 (Open Web Text)

Max Activating Token Index: 995