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

Dataset: Open Web Text

Neuron 37 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: 3.2143. Min Range: -3.2143

Max Act: 3.2143. Min Act: -0.1700

Data Index: 4676223 (Open Web Text)

Max Activating Token Index: 912

Text #1

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.9293. Min Act: -0.1700

Data Index: 3935203 (Open Web Text)

Max Activating Token Index: 174

Text #2

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.9323. Min Act: -0.1700

Data Index: 7542707 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.8518. Min Act: -0.1700

Data Index: 571868 (Open Web Text)

Max Activating Token Index: 568

Text #4

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.8551. Min Act: -0.1700

Data Index: 3113677 (Open Web Text)

Max Activating Token Index: 77

Text #5

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.8323. Min Act: -0.1700

Data Index: 5145313 (Open Web Text)

Max Activating Token Index: 939

Text #6

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.8093. Min Act: -0.1700

Data Index: 8774978 (Open Web Text)

Max Activating Token Index: 755

Text #7

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7989. Min Act: -0.1700

Data Index: 1026988 (Open Web Text)

Max Activating Token Index: 115

Text #8

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7938. Min Act: -0.1700

Data Index: 476710 (Open Web Text)

Max Activating Token Index: 222

Text #9

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7976. Min Act: -0.1700

Data Index: 8631646 (Open Web Text)

Max Activating Token Index: 301

Text #10

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7955. Min Act: -0.1700

Data Index: 78839 (Open Web Text)

Max Activating Token Index: 92

Text #11

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7974. Min Act: -0.1700

Data Index: 4867108 (Open Web Text)

Max Activating Token Index: 82

Text #12

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7931. Min Act: -0.1700

Data Index: 4294641 (Open Web Text)

Max Activating Token Index: 895

Text #13

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7751. Min Act: -0.1700

Data Index: 196016 (Open Web Text)

Max Activating Token Index: 253

Text #14

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7682. Min Act: -0.1700

Data Index: 8625232 (Open Web Text)

Max Activating Token Index: 902

Text #15

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7701. Min Act: -0.1700

Data Index: 4456346 (Open Web Text)

Max Activating Token Index: 429

Text #16

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7656. Min Act: -0.1700

Data Index: 2861692 (Open Web Text)

Max Activating Token Index: 807

Text #17

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7603. Min Act: -0.1700

Data Index: 3110508 (Open Web Text)

Max Activating Token Index: 23

Text #18

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7558. Min Act: -0.1700

Data Index: 3570300 (Open Web Text)

Max Activating Token Index: 978

Text #19

Max Range: 3.2143. Min Range: -3.2143

Max Act: 2.7557. Min Act: -0.1700

Data Index: 84392 (Open Web Text)

Max Activating Token Index: 294