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

Dataset: Open Web Text

Neuron 308 in Layer 0

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: 4.2711. Min Range: -4.2711

Max Act: 4.2711. Min Act: -0.1700

Data Index: 3353705 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.1963. Min Act: -0.1700

Data Index: 5241446 (Open Web Text)

Max Activating Token Index: 676

Text #2

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.1826. Min Act: -0.1700

Data Index: 8175936 (Open Web Text)

Max Activating Token Index: 913

Text #3

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.1422. Min Act: -0.1700

Data Index: 2451572 (Open Web Text)

Max Activating Token Index: 1003

Text #4

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.1607. Min Act: -0.1700

Data Index: 1710268 (Open Web Text)

Max Activating Token Index: 685

Text #5

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.1263. Min Act: -0.1700

Data Index: 4643170 (Open Web Text)

Max Activating Token Index: 686

Text #6

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.1287. Min Act: -0.1700

Data Index: 7891514 (Open Web Text)

Max Activating Token Index: 897

Text #7

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.1160. Min Act: -0.1700

Data Index: 1158841 (Open Web Text)

Max Activating Token Index: 215

Text #8

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.1081. Min Act: -0.1700

Data Index: 7305325 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.1047. Min Act: -0.1700

Data Index: 4180230 (Open Web Text)

Max Activating Token Index: 707

Text #10

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.1258. Min Act: -0.1700

Data Index: 2943120 (Open Web Text)

Max Activating Token Index: 773

Text #11

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0957. Min Act: -0.1700

Data Index: 2025066 (Open Web Text)

Max Activating Token Index: 861

Text #12

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0966. Min Act: -0.1700

Data Index: 856059 (Open Web Text)

Max Activating Token Index: 806

Text #13

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0852. Min Act: -0.1700

Data Index: 7030794 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0982. Min Act: -0.1700

Data Index: 5008575 (Open Web Text)

Max Activating Token Index: 609

Text #15

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0674. Min Act: -0.1700

Data Index: 2220455 (Open Web Text)

Max Activating Token Index: 897

Text #16

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0961. Min Act: -0.1700

Data Index: 7829024 (Open Web Text)

Max Activating Token Index: 749

Text #17

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0897. Min Act: -0.1700

Data Index: 3460554 (Open Web Text)

Max Activating Token Index: 619

Text #18

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0781. Min Act: -0.1700

Data Index: 6933768 (Open Web Text)

Max Activating Token Index: 923

Text #19

Max Range: 4.2711. Min Range: -4.2711

Max Act: 4.0861. Min Act: -0.1700

Data Index: 749346 (Open Web Text)

Max Activating Token Index: 871