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

Dataset: Open Web Text

Neuron 1954 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: 3.4855. Min Range: -3.4855

Max Act: 3.4855. Min Act: -0.1700

Data Index: 7195561 (Open Web Text)

Max Activating Token Index: 825

Text #1

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.4745. Min Act: -0.1700

Data Index: 5690697 (Open Web Text)

Max Activating Token Index: 118

Text #2

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.4472. Min Act: -0.1700

Data Index: 7582917 (Open Web Text)

Max Activating Token Index: 837

Text #3

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.4154. Min Act: -0.1700

Data Index: 3136480 (Open Web Text)

Max Activating Token Index: 869

Text #4

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.4062. Min Act: -0.1700

Data Index: 3558885 (Open Web Text)

Max Activating Token Index: 817

Text #5

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3896. Min Act: -0.1700

Data Index: 4748934 (Open Web Text)

Max Activating Token Index: 1004

Text #6

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3370. Min Act: -0.1700

Data Index: 8630305 (Open Web Text)

Max Activating Token Index: 106

Text #7

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3466. Min Act: -0.1700

Data Index: 798883 (Open Web Text)

Max Activating Token Index: 850

Text #8

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3405. Min Act: -0.1700

Data Index: 4158276 (Open Web Text)

Max Activating Token Index: 403

Text #9

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3488. Min Act: -0.1700

Data Index: 3708031 (Open Web Text)

Max Activating Token Index: 887

Text #10

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3230. Min Act: -0.1700

Data Index: 1770437 (Open Web Text)

Max Activating Token Index: 420

Text #11

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3259. Min Act: -0.1700

Data Index: 7440701 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3240. Min Act: -0.1700

Data Index: 88770 (Open Web Text)

Max Activating Token Index: 711

Text #13

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3334. Min Act: -0.1700

Data Index: 4436655 (Open Web Text)

Max Activating Token Index: 492

Text #14

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3148. Min Act: -0.1700

Data Index: 1580462 (Open Web Text)

Max Activating Token Index: 1003

Text #15

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3367. Min Act: -0.1700

Data Index: 482236 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3058. Min Act: -0.1700

Data Index: 6573863 (Open Web Text)

Max Activating Token Index: 792

Text #17

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3045. Min Act: -0.1700

Data Index: 3250275 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3123. Min Act: -0.1700

Data Index: 8209233 (Open Web Text)

Max Activating Token Index: 319

Text #19

Max Range: 3.4855. Min Range: -3.4855

Max Act: 3.3114. Min Act: -0.1700

Data Index: 6511629 (Open Web Text)

Max Activating Token Index: 103