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

Dataset: Open Web Text

Neuron 2411 in Layer 2

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: 1.8100. Min Range: -1.8100

Max Act: 1.8100. Min Act: -0.1698

Data Index: 3764152 (Open Web Text)

Max Activating Token Index: 106

Text #1

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.7868. Min Act: -0.1700

Data Index: 4637548 (Open Web Text)

Max Activating Token Index: 804

Text #2

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.7452. Min Act: -0.1700

Data Index: 116692 (Open Web Text)

Max Activating Token Index: 711

Text #3

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.7378. Min Act: -0.1700

Data Index: 5059728 (Open Web Text)

Max Activating Token Index: 535

Text #4

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.7403. Min Act: -0.1700

Data Index: 7776025 (Open Web Text)

Max Activating Token Index: 389

Text #5

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.7276. Min Act: -0.1700

Data Index: 5520140 (Open Web Text)

Max Activating Token Index: 661

Text #6

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.7088. Min Act: -0.1700

Data Index: 5572562 (Open Web Text)

Max Activating Token Index: 438

Text #7

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.7091. Min Act: -0.1700

Data Index: 2990191 (Open Web Text)

Max Activating Token Index: 70

Text #8

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.7009. Min Act: -0.1685

Data Index: 2212743 (Open Web Text)

Max Activating Token Index: 596

Text #9

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.7049. Min Act: -0.1699

Data Index: 3916920 (Open Web Text)

Max Activating Token Index: 466

Text #10

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.7051. Min Act: -0.1700

Data Index: 3896015 (Open Web Text)

Max Activating Token Index: 109

Text #11

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6974. Min Act: -0.1700

Data Index: 6476379 (Open Web Text)

Max Activating Token Index: 306

Text #12

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6862. Min Act: -0.1700

Data Index: 5338940 (Open Web Text)

Max Activating Token Index: 357

Text #13

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6801. Min Act: -0.1682

Data Index: 7206917 (Open Web Text)

Max Activating Token Index: 921

Text #14

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6836. Min Act: -0.1700

Data Index: 6712275 (Open Web Text)

Max Activating Token Index: 139

Text #15

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6843. Min Act: -0.1700

Data Index: 2648084 (Open Web Text)

Max Activating Token Index: 68

Text #16

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6939. Min Act: -0.1700

Data Index: 6357401 (Open Web Text)

Max Activating Token Index: 514

Text #17

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6941. Min Act: -0.1700

Data Index: 5885232 (Open Web Text)

Max Activating Token Index: 210

Text #18

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6928. Min Act: -0.1700

Data Index: 2805768 (Open Web Text)

Max Activating Token Index: 594

Text #19

Max Range: 1.8100. Min Range: -1.8100

Max Act: 1.6719. Min Act: -0.1700

Data Index: 3678985 (Open Web Text)

Max Activating Token Index: 605