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

Dataset: Open Web Text

Neuron 441 in Layer 5

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: 4.7609. Min Range: -4.7609

Max Act: 4.7609. Min Act: -0.1700

Data Index: 8740694 (Open Web Text)

Max Activating Token Index: 698

Text #1

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.6601. Min Act: -0.1700

Data Index: 6973165 (Open Web Text)

Max Activating Token Index: 901

Text #2

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.6644. Min Act: -0.1700

Data Index: 8495821 (Open Web Text)

Max Activating Token Index: 537

Text #3

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.6113. Min Act: -0.1700

Data Index: 7946198 (Open Web Text)

Max Activating Token Index: 878

Text #4

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.6018. Min Act: -0.1700

Data Index: 8650187 (Open Web Text)

Max Activating Token Index: 677

Text #5

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.5581. Min Act: -0.1700

Data Index: 5958230 (Open Web Text)

Max Activating Token Index: 427

Text #6

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.5129. Min Act: -0.1700

Data Index: 787412 (Open Web Text)

Max Activating Token Index: 887

Text #7

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.5177. Min Act: -0.1700

Data Index: 3990761 (Open Web Text)

Max Activating Token Index: 872

Text #8

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.5092. Min Act: -0.1700

Data Index: 4645625 (Open Web Text)

Max Activating Token Index: 538

Text #9

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.5055. Min Act: -0.1700

Data Index: 2092245 (Open Web Text)

Max Activating Token Index: 77

Text #10

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.4873. Min Act: -0.1700

Data Index: 6191594 (Open Web Text)

Max Activating Token Index: 981

Text #11

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.4335. Min Act: -0.1700

Data Index: 2125084 (Open Web Text)

Max Activating Token Index: 650

Text #12

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.4486. Min Act: -0.1700

Data Index: 5852505 (Open Web Text)

Max Activating Token Index: 54

Text #13

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.4125. Min Act: -0.1700

Data Index: 3699833 (Open Web Text)

Max Activating Token Index: 838

Text #14

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.4388. Min Act: -0.1700

Data Index: 3431363 (Open Web Text)

Max Activating Token Index: 711

Text #15

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.4317. Min Act: -0.1700

Data Index: 7673452 (Open Web Text)

Max Activating Token Index: 986

Text #16

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.3933. Min Act: -0.1700

Data Index: 2655236 (Open Web Text)

Max Activating Token Index: 788

Text #17

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.3856. Min Act: -0.1700

Data Index: 138541 (Open Web Text)

Max Activating Token Index: 593

Text #18

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.3870. Min Act: -0.1700

Data Index: 4870945 (Open Web Text)

Max Activating Token Index: 88

Text #19

Max Range: 4.7609. Min Range: -4.7609

Max Act: 4.3973. Min Act: -0.1700

Data Index: 5656595 (Open Web Text)

Max Activating Token Index: 881