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

Dataset: Open Web Text

Neuron 1170 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: 3.6510. Min Range: -3.6510

Max Act: 3.6250. Min Act: -0.1700

Data Index: 2159750 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.6510. Min Act: -0.1700

Data Index: 1979411 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5760. Min Act: -0.1700

Data Index: 8119020 (Open Web Text)

Max Activating Token Index: 758

Text #3

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5910. Min Act: -0.1700

Data Index: 6057647 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5996. Min Act: -0.1700

Data Index: 6083704 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5914. Min Act: -0.1700

Data Index: 5384336 (Open Web Text)

Max Activating Token Index: 591

Text #6

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5276. Min Act: -0.1700

Data Index: 5390163 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5522. Min Act: -0.1700

Data Index: 7902429 (Open Web Text)

Max Activating Token Index: 436

Text #8

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5210. Min Act: -0.1700

Data Index: 3707011 (Open Web Text)

Max Activating Token Index: 903

Text #9

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5303. Min Act: -0.1700

Data Index: 6781077 (Open Web Text)

Max Activating Token Index: 824

Text #10

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.4951. Min Act: -0.1700

Data Index: 3183611 (Open Web Text)

Max Activating Token Index: 930

Text #11

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5733. Min Act: -0.1700

Data Index: 7059307 (Open Web Text)

Max Activating Token Index: 486

Text #12

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5184. Min Act: -0.1700

Data Index: 1128914 (Open Web Text)

Max Activating Token Index: 1015

Text #13

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5353. Min Act: -0.1700

Data Index: 7215803 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.4599. Min Act: -0.1700

Data Index: 1209845 (Open Web Text)

Max Activating Token Index: 888

Text #15

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5165. Min Act: -0.1700

Data Index: 1931752 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.4963. Min Act: -0.1700

Data Index: 2953255 (Open Web Text)

Max Activating Token Index: 491

Text #17

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5384. Min Act: -0.1700

Data Index: 2709553 (Open Web Text)

Max Activating Token Index: 162

Text #18

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5012. Min Act: -0.1700

Data Index: 103450 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.6510. Min Range: -3.6510

Max Act: 3.5222. Min Act: -0.1700

Data Index: 3149599 (Open Web Text)

Max Activating Token Index: 36