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

Dataset: Open Web Text

Neuron 1877 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: 3.5481. Min Range: -3.5481

Max Act: 3.5481. Min Act: -0.1700

Data Index: 3722761 (Open Web Text)

Max Activating Token Index: 919

Text #1

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3890. Min Act: -0.1700

Data Index: 5748132 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3705. Min Act: -0.1700

Data Index: 8655847 (Open Web Text)

Max Activating Token Index: 862

Text #3

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3456. Min Act: -0.1700

Data Index: 870043 (Open Web Text)

Max Activating Token Index: 830

Text #4

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3344. Min Act: -0.1700

Data Index: 1166769 (Open Web Text)

Max Activating Token Index: 968

Text #5

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3461. Min Act: -0.1700

Data Index: 2228216 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1990578 (Open Web Text)

Max Activating Token Index: 498

Text #7

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3315. Min Act: -0.1700

Data Index: 6484848 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3287. Min Act: -0.1700

Data Index: 6455971 (Open Web Text)

Max Activating Token Index: 961

Text #9

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3099. Min Act: -0.1700

Data Index: 3689655 (Open Web Text)

Max Activating Token Index: 954

Text #10

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3139. Min Act: -0.1700

Data Index: 8146550 (Open Web Text)

Max Activating Token Index: 314

Text #11

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.2996. Min Act: -0.1700

Data Index: 8619782 (Open Web Text)

Max Activating Token Index: 236

Text #12

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3054. Min Act: -0.1700

Data Index: 4191377 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3178. Min Act: -0.1700

Data Index: 4893840 (Open Web Text)

Max Activating Token Index: 202

Text #14

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3150. Min Act: -0.1700

Data Index: 3464967 (Open Web Text)

Max Activating Token Index: 810

Text #15

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.2869. Min Act: -0.1700

Data Index: 243977 (Open Web Text)

Max Activating Token Index: 343

Text #16

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.2900. Min Act: -0.1700

Data Index: 4023114 (Open Web Text)

Max Activating Token Index: 945

Text #17

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3031. Min Act: -0.1700

Data Index: 663898 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3038. Min Act: -0.1700

Data Index: 1246063 (Open Web Text)

Max Activating Token Index: 397

Text #19

Max Range: 3.5481. Min Range: -3.5481

Max Act: 3.3176. Min Act: -0.1700

Data Index: 1857870 (Open Web Text)

Max Activating Token Index: 209