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

Dataset: Open Web Text

Neuron 45 in Layer 1

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: 4.7930. Min Range: -4.7930

Max Act: 4.7930. Min Act: -0.1700

Data Index: 6324614 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.6748. Min Act: -0.1700

Data Index: 2013191 (Open Web Text)

Max Activating Token Index: 75

Text #2

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.6625. Min Act: -0.1700

Data Index: 7468176 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.6407. Min Act: -0.1700

Data Index: 3509358 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.6369. Min Act: -0.1700

Data Index: 6611048 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5976. Min Act: -0.1700

Data Index: 3374513 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5782. Min Act: -0.1700

Data Index: 2817158 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5551. Min Act: -0.1700

Data Index: 711066 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5365. Min Act: -0.1700

Data Index: 2435021 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5563. Min Act: -0.1700

Data Index: 3410803 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5564. Min Act: -0.1700

Data Index: 5580075 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5353. Min Act: -0.1700

Data Index: 4271466 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5521. Min Act: -0.1700

Data Index: 930627 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5442. Min Act: -0.1700

Data Index: 4727355 (Open Web Text)

Max Activating Token Index: 671

Text #14

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5325. Min Act: -0.1700

Data Index: 6290651 (Open Web Text)

Max Activating Token Index: 122

Text #15

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5354. Min Act: -0.1700

Data Index: 7395071 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5291. Min Act: -0.1700

Data Index: 4958531 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5230. Min Act: -0.1700

Data Index: 3045510 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5443. Min Act: -0.1700

Data Index: 4965025 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.7930. Min Range: -4.7930

Max Act: 4.5524. Min Act: -0.1700

Data Index: 7509388 (Open Web Text)

Max Activating Token Index: 14