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

Dataset: Open Web Text

Neuron 773 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: 3.7349. Min Range: -3.7349

Max Act: 3.7349. Min Act: -0.1700

Data Index: 3369105 (Open Web Text)

Max Activating Token Index: 549

Text #1

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.6886. Min Act: -0.1700

Data Index: 925578 (Open Web Text)

Max Activating Token Index: 308

Text #2

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.6650. Min Act: -0.1700

Data Index: 4381639 (Open Web Text)

Max Activating Token Index: 128

Text #3

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.6316. Min Act: -0.1700

Data Index: 4578893 (Open Web Text)

Max Activating Token Index: 884

Text #4

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.6176. Min Act: -0.1700

Data Index: 2522647 (Open Web Text)

Max Activating Token Index: 85

Text #5

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.6011. Min Act: -0.1700

Data Index: 3757741 (Open Web Text)

Max Activating Token Index: 982

Text #6

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.5137. Min Act: -0.1700

Data Index: 1260851 (Open Web Text)

Max Activating Token Index: 429

Text #7

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.5395. Min Act: -0.1700

Data Index: 4063865 (Open Web Text)

Max Activating Token Index: 507

Text #8

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.5278. Min Act: -0.1700

Data Index: 8057409 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.5336. Min Act: -0.1700

Data Index: 3568112 (Open Web Text)

Max Activating Token Index: 340

Text #10

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.5019. Min Act: -0.1700

Data Index: 7994703 (Open Web Text)

Max Activating Token Index: 180

Text #11

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.5066. Min Act: -0.1700

Data Index: 967469 (Open Web Text)

Max Activating Token Index: 274

Text #12

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.4994. Min Act: -0.1700

Data Index: 7058313 (Open Web Text)

Max Activating Token Index: 166

Text #13

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.5043. Min Act: -0.1700

Data Index: 6263596 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.4822. Min Act: -0.1700

Data Index: 2351603 (Open Web Text)

Max Activating Token Index: 943

Text #15

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.4827. Min Act: -0.1700

Data Index: 8020161 (Open Web Text)

Max Activating Token Index: 152

Text #16

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.4801. Min Act: -0.1700

Data Index: 5194717 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.4716. Min Act: -0.1700

Data Index: 8348105 (Open Web Text)

Max Activating Token Index: 979

Text #18

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.4675. Min Act: -0.1700

Data Index: 8439275 (Open Web Text)

Max Activating Token Index: 969

Text #19

Max Range: 3.7349. Min Range: -3.7349

Max Act: 3.4590. Min Act: -0.1700

Data Index: 8240969 (Open Web Text)

Max Activating Token Index: 408