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

Dataset: Open Web Text

Neuron 2671 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: 6.5503. Min Range: -6.5503

Max Act: 6.5034. Min Act: -0.1700

Data Index: 1580718 (Open Web Text)

Max Activating Token Index: 1021

Text #1

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.5132. Min Act: -0.1700

Data Index: 832981 (Open Web Text)

Max Activating Token Index: 878

Text #2

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.5380. Min Act: -0.1700

Data Index: 4607715 (Open Web Text)

Max Activating Token Index: 982

Text #3

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4970. Min Act: -0.1700

Data Index: 2991152 (Open Web Text)

Max Activating Token Index: 876

Text #4

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4962. Min Act: -0.1700

Data Index: 6949108 (Open Web Text)

Max Activating Token Index: 878

Text #5

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.5503. Min Act: -0.1700

Data Index: 3691575 (Open Web Text)

Max Activating Token Index: 723

Text #6

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4724. Min Act: -0.1700

Data Index: 1926170 (Open Web Text)

Max Activating Token Index: 982

Text #7

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4955. Min Act: -0.1700

Data Index: 3678582 (Open Web Text)

Max Activating Token Index: 840

Text #8

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4835. Min Act: -0.1700

Data Index: 1634957 (Open Web Text)

Max Activating Token Index: 104

Text #9

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4455. Min Act: -0.1700

Data Index: 1634952 (Open Web Text)

Max Activating Token Index: 806

Text #10

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4546. Min Act: -0.1700

Data Index: 3797435 (Open Web Text)

Max Activating Token Index: 676

Text #11

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4742. Min Act: -0.1700

Data Index: 5443236 (Open Web Text)

Max Activating Token Index: 953

Text #12

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4885. Min Act: -0.1700

Data Index: 7726466 (Open Web Text)

Max Activating Token Index: 514

Text #13

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4384. Min Act: -0.1700

Data Index: 8367081 (Open Web Text)

Max Activating Token Index: 436

Text #14

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4577. Min Act: -0.1700

Data Index: 2177698 (Open Web Text)

Max Activating Token Index: 543

Text #15

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4321. Min Act: -0.1700

Data Index: 1632332 (Open Web Text)

Max Activating Token Index: 1015

Text #16

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4452. Min Act: -0.1700

Data Index: 4949550 (Open Web Text)

Max Activating Token Index: 816

Text #17

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4426. Min Act: -0.1700

Data Index: 6452849 (Open Web Text)

Max Activating Token Index: 337

Text #18

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.4047. Min Act: -0.1700

Data Index: 4607719 (Open Web Text)

Max Activating Token Index: 675

Text #19

Max Range: 6.5503. Min Range: -6.5503

Max Act: 6.3833. Min Act: -0.1700

Data Index: 1900774 (Open Web Text)

Max Activating Token Index: 113