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

Dataset: Open Web Text

Neuron 129 in Layer 4

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: 2.9944. Min Range: -2.9944

Max Act: 2.9944. Min Act: -0.1700

Data Index: 2938469 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.8724. Min Act: -0.1700

Data Index: 6846085 (Open Web Text)

Max Activating Token Index: 899

Text #2

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.8140. Min Act: -0.1700

Data Index: 1657063 (Open Web Text)

Max Activating Token Index: 960

Text #3

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.8116. Min Act: -0.1700

Data Index: 6729378 (Open Web Text)

Max Activating Token Index: 847

Text #4

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7937. Min Act: -0.1700

Data Index: 5834969 (Open Web Text)

Max Activating Token Index: 456

Text #5

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7562. Min Act: -0.1700

Data Index: 6322991 (Open Web Text)

Max Activating Token Index: 106

Text #6

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7604. Min Act: -0.1700

Data Index: 3659460 (Open Web Text)

Max Activating Token Index: 836

Text #7

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7512. Min Act: -0.1700

Data Index: 2703209 (Open Web Text)

Max Activating Token Index: 86

Text #8

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7063. Min Act: -0.1700

Data Index: 6317785 (Open Web Text)

Max Activating Token Index: 537

Text #9

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7165. Min Act: -0.1700

Data Index: 3656798 (Open Web Text)

Max Activating Token Index: 231

Text #10

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7345. Min Act: -0.1700

Data Index: 3528755 (Open Web Text)

Max Activating Token Index: 637

Text #11

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7477. Min Act: -0.1700

Data Index: 6043779 (Open Web Text)

Max Activating Token Index: 1003

Text #12

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7547. Min Act: -0.1700

Data Index: 2741570 (Open Web Text)

Max Activating Token Index: 726

Text #13

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7541. Min Act: -0.1700

Data Index: 5086739 (Open Web Text)

Max Activating Token Index: 458

Text #14

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7334. Min Act: -0.1700

Data Index: 7628073 (Open Web Text)

Max Activating Token Index: 418

Text #15

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7313. Min Act: -0.1700

Data Index: 88200 (Open Web Text)

Max Activating Token Index: 821

Text #16

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7351. Min Act: -0.1700

Data Index: 1684363 (Open Web Text)

Max Activating Token Index: 119

Text #17

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7368. Min Act: -0.1700

Data Index: 5314084 (Open Web Text)

Max Activating Token Index: 276

Text #18

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7216. Min Act: -0.1700

Data Index: 7958113 (Open Web Text)

Max Activating Token Index: 69

Text #19

Max Range: 2.9944. Min Range: -2.9944

Max Act: 2.7440. Min Act: -0.1700

Data Index: 1235542 (Open Web Text)

Max Activating Token Index: 553