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

Dataset: Open Web Text

Neuron 1944 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: 4.6469. Min Range: -4.6469

Max Act: 4.6286. Min Act: -0.1700

Data Index: 4219773 (Open Web Text)

Max Activating Token Index: 109

Text #1

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.6469. Min Act: -0.1700

Data Index: 5910597 (Open Web Text)

Max Activating Token Index: 484

Text #2

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.5545. Min Act: -0.1700

Data Index: 2391284 (Open Web Text)

Max Activating Token Index: 305

Text #3

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.5494. Min Act: -0.1700

Data Index: 6917397 (Open Web Text)

Max Activating Token Index: 1019

Text #4

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.5284. Min Act: -0.1700

Data Index: 1209325 (Open Web Text)

Max Activating Token Index: 539

Text #5

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.5032. Min Act: -0.1700

Data Index: 1692510 (Open Web Text)

Max Activating Token Index: 721

Text #6

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.4767. Min Act: -0.1700

Data Index: 8378125 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.4487. Min Act: -0.1700

Data Index: 2785042 (Open Web Text)

Max Activating Token Index: 895

Text #8

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.4643. Min Act: -0.1700

Data Index: 8571029 (Open Web Text)

Max Activating Token Index: 485

Text #9

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.4685. Min Act: -0.1700

Data Index: 5340714 (Open Web Text)

Max Activating Token Index: 826

Text #10

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.4342. Min Act: -0.1700

Data Index: 4146104 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.4394. Min Act: -0.1700

Data Index: 1636869 (Open Web Text)

Max Activating Token Index: 584

Text #12

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.4114. Min Act: -0.1700

Data Index: 594098 (Open Web Text)

Max Activating Token Index: 980

Text #13

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.4121. Min Act: -0.1700

Data Index: 2634732 (Open Web Text)

Max Activating Token Index: 352

Text #14

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.3793. Min Act: -0.1700

Data Index: 42969 (Open Web Text)

Max Activating Token Index: 951

Text #15

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.3977. Min Act: -0.1700

Data Index: 6874259 (Open Web Text)

Max Activating Token Index: 341

Text #16

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.4053. Min Act: -0.1700

Data Index: 4576433 (Open Web Text)

Max Activating Token Index: 955

Text #17

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.3637. Min Act: -0.1700

Data Index: 1880940 (Open Web Text)

Max Activating Token Index: 103

Text #18

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.3497. Min Act: -0.1700

Data Index: 1462771 (Open Web Text)

Max Activating Token Index: 89

Text #19

Max Range: 4.6469. Min Range: -4.6469

Max Act: 4.3516. Min Act: -0.1700

Data Index: 1502327 (Open Web Text)

Max Activating Token Index: 1018