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

Dataset: Open Web Text

Neuron 1742 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: 3.1670. Min Range: -3.1670

Max Act: 3.1670. Min Act: -0.1700

Data Index: 3377235 (Open Web Text)

Max Activating Token Index: 596

Text #1

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.1526. Min Act: -0.1700

Data Index: 3110459 (Open Web Text)

Max Activating Token Index: 706

Text #2

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.1141. Min Act: -0.1700

Data Index: 7696859 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0982. Min Act: -0.1700

Data Index: 7117824 (Open Web Text)

Max Activating Token Index: 105

Text #4

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0878. Min Act: -0.1700

Data Index: 144599 (Open Web Text)

Max Activating Token Index: 954

Text #5

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0823. Min Act: -0.1700

Data Index: 2139141 (Open Web Text)

Max Activating Token Index: 844

Text #6

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0746. Min Act: -0.1700

Data Index: 1481135 (Open Web Text)

Max Activating Token Index: 760

Text #7

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0641. Min Act: -0.1700

Data Index: 7864534 (Open Web Text)

Max Activating Token Index: 443

Text #8

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0974. Min Act: -0.1700

Data Index: 2712661 (Open Web Text)

Max Activating Token Index: 654

Text #9

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0525. Min Act: -0.1700

Data Index: 3671314 (Open Web Text)

Max Activating Token Index: 932

Text #10

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0460. Min Act: -0.1700

Data Index: 5901121 (Open Web Text)

Max Activating Token Index: 160

Text #11

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0033. Min Act: -0.1700

Data Index: 3488681 (Open Web Text)

Max Activating Token Index: 247

Text #12

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0092. Min Act: -0.1700

Data Index: 2415923 (Open Web Text)

Max Activating Token Index: 611

Text #13

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0163. Min Act: -0.1700

Data Index: 5274944 (Open Web Text)

Max Activating Token Index: 936

Text #14

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0160. Min Act: -0.1700

Data Index: 4831179 (Open Web Text)

Max Activating Token Index: 162

Text #15

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0380. Min Act: -0.1700

Data Index: 1404057 (Open Web Text)

Max Activating Token Index: 714

Text #16

Max Range: 3.1670. Min Range: -3.1670

Max Act: 3.0035. Min Act: -0.1700

Data Index: 5319740 (Open Web Text)

Max Activating Token Index: 612

Text #17

Max Range: 3.1670. Min Range: -3.1670

Max Act: 2.9894. Min Act: -0.1700

Data Index: 520079 (Open Web Text)

Max Activating Token Index: 248

Text #18

Max Range: 3.1670. Min Range: -3.1670

Max Act: 2.9517. Min Act: -0.1700

Data Index: 1264477 (Open Web Text)

Max Activating Token Index: 78

Text #19

Max Range: 3.1670. Min Range: -3.1670

Max Act: 2.9631. Min Act: -0.1700

Data Index: 2517499 (Open Web Text)

Max Activating Token Index: 910