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

Dataset: Open Web Text

Neuron 1145 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: 4.8436. Min Range: -4.8436

Max Act: 4.8436. Min Act: -0.1700

Data Index: 4039203 (Open Web Text)

Max Activating Token Index: 876

Text #1

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.7590. Min Act: -0.1700

Data Index: 8393262 (Open Web Text)

Max Activating Token Index: 73

Text #2

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.7725. Min Act: -0.1700

Data Index: 4633746 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.7357. Min Act: -0.1700

Data Index: 4115615 (Open Web Text)

Max Activating Token Index: 882

Text #4

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.7505. Min Act: -0.1700

Data Index: 5817380 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.7580. Min Act: -0.1700

Data Index: 4886847 (Open Web Text)

Max Activating Token Index: 313

Text #6

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.7235. Min Act: -0.1700

Data Index: 7445025 (Open Web Text)

Max Activating Token Index: 398

Text #7

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.6774. Min Act: -0.1700

Data Index: 7505802 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.7228. Min Act: -0.1700

Data Index: 6648423 (Open Web Text)

Max Activating Token Index: 306

Text #9

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.6559. Min Act: -0.1700

Data Index: 3740883 (Open Web Text)

Max Activating Token Index: 418

Text #10

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.6405. Min Act: -0.1700

Data Index: 7063283 (Open Web Text)

Max Activating Token Index: 692

Text #11

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.6681. Min Act: -0.1700

Data Index: 3403200 (Open Web Text)

Max Activating Token Index: 335

Text #12

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.6583. Min Act: -0.1700

Data Index: 2305966 (Open Web Text)

Max Activating Token Index: 810

Text #13

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.6098. Min Act: -0.1700

Data Index: 6949974 (Open Web Text)

Max Activating Token Index: 532

Text #14

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.6262. Min Act: -0.1700

Data Index: 316923 (Open Web Text)

Max Activating Token Index: 597

Text #15

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.5615. Min Act: -0.1700

Data Index: 7150217 (Open Web Text)

Max Activating Token Index: 656

Text #16

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.5867. Min Act: -0.1700

Data Index: 7779898 (Open Web Text)

Max Activating Token Index: 181

Text #17

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.6452. Min Act: -0.1700

Data Index: 7751719 (Open Web Text)

Max Activating Token Index: 537

Text #18

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.5948. Min Act: -0.1700

Data Index: 7377201 (Open Web Text)

Max Activating Token Index: 859

Text #19

Max Range: 4.8436. Min Range: -4.8436

Max Act: 4.6311. Min Act: -0.1700

Data Index: 2816186 (Open Web Text)

Max Activating Token Index: 754