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

Dataset: Open Web Text

Neuron 449 in Layer 2

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: 3.3155. Min Range: -3.3155

Max Act: 3.3155. Min Act: -0.1700

Data Index: 5544202 (Open Web Text)

Max Activating Token Index: 970

Text #1

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.3090. Min Act: -0.1700

Data Index: 6061176 (Open Web Text)

Max Activating Token Index: 382

Text #2

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2905. Min Act: -0.1700

Data Index: 3702763 (Open Web Text)

Max Activating Token Index: 538

Text #3

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.3084. Min Act: -0.1700

Data Index: 8436976 (Open Web Text)

Max Activating Token Index: 565

Text #4

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2874. Min Act: -0.1700

Data Index: 8575980 (Open Web Text)

Max Activating Token Index: 954

Text #5

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2620. Min Act: -0.1700

Data Index: 5537456 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2095. Min Act: -0.1700

Data Index: 8490585 (Open Web Text)

Max Activating Token Index: 871

Text #7

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2351. Min Act: -0.1700

Data Index: 692955 (Open Web Text)

Max Activating Token Index: 488

Text #8

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2067. Min Act: -0.1700

Data Index: 7960756 (Open Web Text)

Max Activating Token Index: 220

Text #9

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2037. Min Act: -0.1700

Data Index: 5209239 (Open Web Text)

Max Activating Token Index: 987

Text #10

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2080. Min Act: -0.1700

Data Index: 7161793 (Open Web Text)

Max Activating Token Index: 707

Text #11

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2130. Min Act: -0.1700

Data Index: 4500001 (Open Web Text)

Max Activating Token Index: 198

Text #12

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.1972. Min Act: -0.1700

Data Index: 3437288 (Open Web Text)

Max Activating Token Index: 86

Text #13

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.2029. Min Act: -0.1700

Data Index: 6098623 (Open Web Text)

Max Activating Token Index: 1021

Text #14

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.1886. Min Act: -0.1700

Data Index: 696499 (Open Web Text)

Max Activating Token Index: 953

Text #15

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.1716. Min Act: -0.1700

Data Index: 2088531 (Open Web Text)

Max Activating Token Index: 476

Text #16

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.1988. Min Act: -0.1700

Data Index: 2996137 (Open Web Text)

Max Activating Token Index: 209

Text #17

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.1628. Min Act: -0.1700

Data Index: 5089698 (Open Web Text)

Max Activating Token Index: 504

Text #18

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.1804. Min Act: -0.1700

Data Index: 5347720 (Open Web Text)

Max Activating Token Index: 576

Text #19

Max Range: 3.3155. Min Range: -3.3155

Max Act: 3.1487. Min Act: -0.1700

Data Index: 5029875 (Open Web Text)

Max Activating Token Index: 426