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

Dataset: Open Web Text

Neuron 2603 in Layer 3

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: 3.4729. Min Range: -3.4729

Max Act: 3.4729. Min Act: -0.1700

Data Index: 4062396 (Open Web Text)

Max Activating Token Index: 629

Text #1

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.3089. Min Act: -0.1700

Data Index: 7455382 (Open Web Text)

Max Activating Token Index: 148

Text #2

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2806. Min Act: -0.1700

Data Index: 8825594 (Open Web Text)

Max Activating Token Index: 556

Text #3

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2350. Min Act: -0.1700

Data Index: 4307974 (Open Web Text)

Max Activating Token Index: 954

Text #4

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2794. Min Act: -0.1700

Data Index: 7549942 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2060. Min Act: -0.1700

Data Index: 163697 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2342. Min Act: -0.1700

Data Index: 1166146 (Open Web Text)

Max Activating Token Index: 399

Text #7

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2058. Min Act: -0.1700

Data Index: 5366263 (Open Web Text)

Max Activating Token Index: 461

Text #8

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2738. Min Act: -0.1700

Data Index: 5251285 (Open Web Text)

Max Activating Token Index: 903

Text #9

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2047. Min Act: -0.1700

Data Index: 2734162 (Open Web Text)

Max Activating Token Index: 377

Text #10

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2910. Min Act: -0.1700

Data Index: 6717767 (Open Web Text)

Max Activating Token Index: 963

Text #11

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2225. Min Act: -0.1700

Data Index: 754770 (Open Web Text)

Max Activating Token Index: 881

Text #12

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1978. Min Act: -0.1700

Data Index: 3744965 (Open Web Text)

Max Activating Token Index: 379

Text #13

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1493. Min Act: -0.1700

Data Index: 2654832 (Open Web Text)

Max Activating Token Index: 966

Text #14

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1423. Min Act: -0.1700

Data Index: 8749775 (Open Web Text)

Max Activating Token Index: 432

Text #15

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1990. Min Act: -0.1700

Data Index: 7079595 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2046. Min Act: -0.1700

Data Index: 1651309 (Open Web Text)

Max Activating Token Index: 226

Text #17

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2131. Min Act: -0.1700

Data Index: 8595465 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.2133. Min Act: -0.1700

Data Index: 2552615 (Open Web Text)

Max Activating Token Index: 557

Text #19

Max Range: 3.4729. Min Range: -3.4729

Max Act: 3.1123. Min Act: -0.1700

Data Index: 5491181 (Open Web Text)

Max Activating Token Index: 184