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

Dataset: Open Web Text

Neuron 266 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: 2.5372. Min Range: -2.5372

Max Act: 2.5372. Min Act: -0.1700

Data Index: 4978165 (Open Web Text)

Max Activating Token Index: 900

Text #1

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.5247. Min Act: -0.1700

Data Index: 5300015 (Open Web Text)

Max Activating Token Index: 851

Text #2

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.4749. Min Act: -0.1700

Data Index: 4603997 (Open Web Text)

Max Activating Token Index: 53

Text #3

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.4274. Min Act: -0.1700

Data Index: 6566237 (Open Web Text)

Max Activating Token Index: 438

Text #4

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.4503. Min Act: -0.1700

Data Index: 1071776 (Open Web Text)

Max Activating Token Index: 723

Text #5

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.4455. Min Act: -0.1700

Data Index: 4290950 (Open Web Text)

Max Activating Token Index: 222

Text #6

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.4363. Min Act: -0.1700

Data Index: 901954 (Open Web Text)

Max Activating Token Index: 472

Text #7

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.3946. Min Act: -0.1700

Data Index: 1061987 (Open Web Text)

Max Activating Token Index: 405

Text #8

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.4027. Min Act: -0.1700

Data Index: 1071457 (Open Web Text)

Max Activating Token Index: 787

Text #9

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.4030. Min Act: -0.1700

Data Index: 1386865 (Open Web Text)

Max Activating Token Index: 678

Text #10

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.3751. Min Act: -0.1700

Data Index: 6900356 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.3734. Min Act: -0.1700

Data Index: 8366334 (Open Web Text)

Max Activating Token Index: 857

Text #12

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.3687. Min Act: -0.1700

Data Index: 1031120 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.3745. Min Act: -0.1700

Data Index: 2523304 (Open Web Text)

Max Activating Token Index: 934

Text #14

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.3739. Min Act: -0.1700

Data Index: 558815 (Open Web Text)

Max Activating Token Index: 938

Text #15

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.3761. Min Act: -0.1700

Data Index: 7301085 (Open Web Text)

Max Activating Token Index: 669

Text #16

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.3375. Min Act: -0.1700

Data Index: 5676802 (Open Web Text)

Max Activating Token Index: 846

Text #17

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.3501. Min Act: -0.1700

Data Index: 6042435 (Open Web Text)

Max Activating Token Index: 49

Text #18

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.3448. Min Act: -0.1700

Data Index: 5636702 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 2.5372. Min Range: -2.5372

Max Act: 2.3496. Min Act: -0.1700

Data Index: 4563180 (Open Web Text)

Max Activating Token Index: 5