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

Dataset: Open Web Text

Neuron 922 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: 3.3032. Min Range: -3.3032

Max Act: 3.3032. Min Act: -0.1700

Data Index: 6905569 (Open Web Text)

Max Activating Token Index: 749

Text #1

Max Range: 3.3032. Min Range: -3.3032

Max Act: 3.1607. Min Act: -0.1700

Data Index: 4616148 (Open Web Text)

Max Activating Token Index: 481

Text #2

Max Range: 3.3032. Min Range: -3.3032

Max Act: 3.0844. Min Act: -0.1700

Data Index: 1989055 (Open Web Text)

Max Activating Token Index: 240

Text #3

Max Range: 3.3032. Min Range: -3.3032

Max Act: 3.0389. Min Act: -0.1700

Data Index: 1642948 (Open Web Text)

Max Activating Token Index: 404

Text #4

Max Range: 3.3032. Min Range: -3.3032

Max Act: 3.0026. Min Act: -0.1700

Data Index: 5318710 (Open Web Text)

Max Activating Token Index: 707

Text #5

Max Range: 3.3032. Min Range: -3.3032

Max Act: 3.0209. Min Act: -0.1700

Data Index: 2723853 (Open Web Text)

Max Activating Token Index: 908

Text #6

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.9973. Min Act: -0.1700

Data Index: 4356105 (Open Web Text)

Max Activating Token Index: 948

Text #7

Max Range: 3.3032. Min Range: -3.3032

Max Act: 3.0052. Min Act: -0.1700

Data Index: 1256340 (Open Web Text)

Max Activating Token Index: 117

Text #8

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.9816. Min Act: -0.1700

Data Index: 1860731 (Open Web Text)

Max Activating Token Index: 889

Text #9

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.9621. Min Act: -0.1700

Data Index: 228150 (Open Web Text)

Max Activating Token Index: 982

Text #10

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.9683. Min Act: -0.1700

Data Index: 935552 (Open Web Text)

Max Activating Token Index: 749

Text #11

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.9386. Min Act: -0.1700

Data Index: 3342656 (Open Web Text)

Max Activating Token Index: 416

Text #12

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.8996. Min Act: -0.1700

Data Index: 4291194 (Open Web Text)

Max Activating Token Index: 797

Text #13

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.9080. Min Act: -0.1700

Data Index: 6860884 (Open Web Text)

Max Activating Token Index: 231

Text #14

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.8783. Min Act: -0.1700

Data Index: 3355186 (Open Web Text)

Max Activating Token Index: 437

Text #15

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.9082. Min Act: -0.1700

Data Index: 1836321 (Open Web Text)

Max Activating Token Index: 278

Text #16

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.8892. Min Act: -0.1700

Data Index: 6033664 (Open Web Text)

Max Activating Token Index: 464

Text #17

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.8884. Min Act: -0.1700

Data Index: 3038109 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.9200. Min Act: -0.1700

Data Index: 6487797 (Open Web Text)

Max Activating Token Index: 284

Text #19

Max Range: 3.3032. Min Range: -3.3032

Max Act: 2.8816. Min Act: -0.1700

Data Index: 7565802 (Open Web Text)

Max Activating Token Index: 465