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

Dataset: Open Web Text

Neuron 2908 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: 3.7954. Min Range: -3.7954

Max Act: 3.7954. Min Act: -0.1700

Data Index: 8157435 (Open Web Text)

Max Activating Token Index: 427

Text #1

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.7503. Min Act: -0.1700

Data Index: 4032605 (Open Web Text)

Max Activating Token Index: 191

Text #2

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.6719. Min Act: -0.1700

Data Index: 4469423 (Open Web Text)

Max Activating Token Index: 928

Text #3

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.6434. Min Act: -0.1700

Data Index: 411925 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.6206. Min Act: -0.1700

Data Index: 1026449 (Open Web Text)

Max Activating Token Index: 933

Text #5

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.6493. Min Act: -0.1700

Data Index: 8409002 (Open Web Text)

Max Activating Token Index: 220

Text #6

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.6431. Min Act: -0.1700

Data Index: 2851620 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.5961. Min Act: -0.1700

Data Index: 8006157 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.5833. Min Act: -0.1700

Data Index: 2551614 (Open Web Text)

Max Activating Token Index: 154

Text #9

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.5633. Min Act: -0.1700

Data Index: 5862148 (Open Web Text)

Max Activating Token Index: 647

Text #10

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.5784. Min Act: -0.1700

Data Index: 7730298 (Open Web Text)

Max Activating Token Index: 204

Text #11

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.5401. Min Act: -0.1700

Data Index: 756234 (Open Web Text)

Max Activating Token Index: 768

Text #12

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.5299. Min Act: -0.1700

Data Index: 7012288 (Open Web Text)

Max Activating Token Index: 243

Text #13

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.5020. Min Act: -0.1700

Data Index: 8312213 (Open Web Text)

Max Activating Token Index: 520

Text #14

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.5255. Min Act: -0.1700

Data Index: 6763055 (Open Web Text)

Max Activating Token Index: 579

Text #15

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.4808. Min Act: -0.1700

Data Index: 6386860 (Open Web Text)

Max Activating Token Index: 725

Text #16

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.5271. Min Act: -0.1700

Data Index: 7445914 (Open Web Text)

Max Activating Token Index: 738

Text #17

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.4887. Min Act: -0.1700

Data Index: 8021404 (Open Web Text)

Max Activating Token Index: 591

Text #18

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.4862. Min Act: -0.1700

Data Index: 6791989 (Open Web Text)

Max Activating Token Index: 894

Text #19

Max Range: 3.7954. Min Range: -3.7954

Max Act: 3.4994. Min Act: -0.1700

Data Index: 5515641 (Open Web Text)

Max Activating Token Index: 981