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

Dataset: Open Web Text

Neuron 1853 in Layer 6

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: 3.1197. Min Range: -3.1197

Max Act: 3.1197. Min Act: -0.1700

Data Index: 3438277 (Open Web Text)

Max Activating Token Index: 363

Text #1

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.9897. Min Act: -0.1700

Data Index: 3438276 (Open Web Text)

Max Activating Token Index: 922

Text #2

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.8686. Min Act: -0.1700

Data Index: 6129787 (Open Web Text)

Max Activating Token Index: 907

Text #3

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.8528. Min Act: -0.1700

Data Index: 6623006 (Open Web Text)

Max Activating Token Index: 258

Text #4

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.8392. Min Act: -0.1700

Data Index: 4939022 (Open Web Text)

Max Activating Token Index: 933

Text #5

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.8543. Min Act: -0.1700

Data Index: 5425938 (Open Web Text)

Max Activating Token Index: 459

Text #6

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.8135. Min Act: -0.1700

Data Index: 3312758 (Open Web Text)

Max Activating Token Index: 461

Text #7

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7906. Min Act: -0.1700

Data Index: 8794861 (Open Web Text)

Max Activating Token Index: 992

Text #8

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7936. Min Act: -0.1700

Data Index: 4939047 (Open Web Text)

Max Activating Token Index: 887

Text #9

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7816. Min Act: -0.1700

Data Index: 3312764 (Open Web Text)

Max Activating Token Index: 694

Text #10

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7573. Min Act: -0.1700

Data Index: 8158005 (Open Web Text)

Max Activating Token Index: 880

Text #11

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7723. Min Act: -0.1700

Data Index: 4241761 (Open Web Text)

Max Activating Token Index: 372

Text #12

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7376. Min Act: -0.1700

Data Index: 2142736 (Open Web Text)

Max Activating Token Index: 155

Text #13

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7634. Min Act: -0.1700

Data Index: 7184234 (Open Web Text)

Max Activating Token Index: 886

Text #14

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7452. Min Act: -0.1700

Data Index: 6485717 (Open Web Text)

Max Activating Token Index: 989

Text #15

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7306. Min Act: -0.1700

Data Index: 7320571 (Open Web Text)

Max Activating Token Index: 982

Text #16

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7372. Min Act: -0.1700

Data Index: 1348054 (Open Web Text)

Max Activating Token Index: 492

Text #17

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7326. Min Act: -0.1700

Data Index: 7267932 (Open Web Text)

Max Activating Token Index: 966

Text #18

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.7330. Min Act: -0.1700

Data Index: 6721093 (Open Web Text)

Max Activating Token Index: 364

Text #19

Max Range: 3.1197. Min Range: -3.1197

Max Act: 2.6938. Min Act: -0.1700

Data Index: 8405492 (Open Web Text)

Max Activating Token Index: 380