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

Dataset: Open Web Text

Neuron 2241 in Layer 6

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: 3.9646. Min Range: -3.9646

Max Act: 3.9646. Min Act: -0.1700

Data Index: 8128385 (Open Web Text)

Max Activating Token Index: 975

Text #1

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.7796. Min Act: -0.1700

Data Index: 1275231 (Open Web Text)

Max Activating Token Index: 764

Text #2

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.7500. Min Act: -0.1700

Data Index: 8599707 (Open Web Text)

Max Activating Token Index: 951

Text #3

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6849. Min Act: -0.1700

Data Index: 5432562 (Open Web Text)

Max Activating Token Index: 798

Text #4

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6897. Min Act: -0.1700

Data Index: 564872 (Open Web Text)

Max Activating Token Index: 981

Text #5

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6778. Min Act: -0.1700

Data Index: 7370595 (Open Web Text)

Max Activating Token Index: 162

Text #6

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6722. Min Act: -0.1700

Data Index: 1339138 (Open Web Text)

Max Activating Token Index: 552

Text #7

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6655. Min Act: -0.1700

Data Index: 7707846 (Open Web Text)

Max Activating Token Index: 56

Text #8

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6489. Min Act: -0.1700

Data Index: 4846091 (Open Web Text)

Max Activating Token Index: 826

Text #9

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6326. Min Act: -0.1700

Data Index: 6290252 (Open Web Text)

Max Activating Token Index: 677

Text #10

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6440. Min Act: -0.1700

Data Index: 2118944 (Open Web Text)

Max Activating Token Index: 37

Text #11

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6516. Min Act: -0.1700

Data Index: 8336139 (Open Web Text)

Max Activating Token Index: 832

Text #12

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6432. Min Act: -0.1700

Data Index: 6048228 (Open Web Text)

Max Activating Token Index: 277

Text #13

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6698. Min Act: -0.1700

Data Index: 5538933 (Open Web Text)

Max Activating Token Index: 916

Text #14

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6437. Min Act: -0.1700

Data Index: 4895293 (Open Web Text)

Max Activating Token Index: 152

Text #15

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6341. Min Act: -0.1700

Data Index: 6860231 (Open Web Text)

Max Activating Token Index: 252

Text #16

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6258. Min Act: -0.1700

Data Index: 3548161 (Open Web Text)

Max Activating Token Index: 747

Text #17

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6302. Min Act: -0.1700

Data Index: 7661870 (Open Web Text)

Max Activating Token Index: 280

Text #18

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6342. Min Act: -0.1700

Data Index: 7270610 (Open Web Text)

Max Activating Token Index: 692

Text #19

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6073. Min Act: -0.1700

Data Index: 6216551 (Open Web Text)

Max Activating Token Index: 145