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

Dataset: Open Web Text

Neuron 2556 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: 5.9620. Min Range: -5.9620

Max Act: 5.9581. Min Act: -0.1700

Data Index: 1827114 (Open Web Text)

Max Activating Token Index: 338

Text #1

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.9620. Min Act: -0.1700

Data Index: 2161014 (Open Web Text)

Max Activating Token Index: 969

Text #2

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.9140. Min Act: -0.1700

Data Index: 103109 (Open Web Text)

Max Activating Token Index: 133

Text #3

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.8893. Min Act: -0.1700

Data Index: 6645491 (Open Web Text)

Max Activating Token Index: 328

Text #4

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.8801. Min Act: -0.1700

Data Index: 7472046 (Open Web Text)

Max Activating Token Index: 808

Text #5

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.8398. Min Act: -0.1700

Data Index: 8378108 (Open Web Text)

Max Activating Token Index: 869

Text #6

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.8424. Min Act: -0.1700

Data Index: 5672313 (Open Web Text)

Max Activating Token Index: 772

Text #7

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.7742. Min Act: -0.1700

Data Index: 347245 (Open Web Text)

Max Activating Token Index: 840

Text #8

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.6427. Min Act: -0.1700

Data Index: 8291331 (Open Web Text)

Max Activating Token Index: 894

Text #9

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.6202. Min Act: -0.1700

Data Index: 5063109 (Open Web Text)

Max Activating Token Index: 611

Text #10

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.5774. Min Act: -0.1700

Data Index: 6089379 (Open Web Text)

Max Activating Token Index: 171

Text #11

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.5038. Min Act: -0.1700

Data Index: 7599244 (Open Web Text)

Max Activating Token Index: 384

Text #12

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.4481. Min Act: -0.1700

Data Index: 2031076 (Open Web Text)

Max Activating Token Index: 467

Text #13

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.4389. Min Act: -0.1700

Data Index: 1298020 (Open Web Text)

Max Activating Token Index: 384

Text #14

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.3240. Min Act: -0.1700

Data Index: 2804100 (Open Web Text)

Max Activating Token Index: 586

Text #15

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.3654. Min Act: -0.1700

Data Index: 1668217 (Open Web Text)

Max Activating Token Index: 770

Text #16

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.3561. Min Act: -0.1700

Data Index: 5717745 (Open Web Text)

Max Activating Token Index: 183

Text #17

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.3569. Min Act: -0.1700

Data Index: 7413155 (Open Web Text)

Max Activating Token Index: 366

Text #18

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.2931. Min Act: -0.1700

Data Index: 6453492 (Open Web Text)

Max Activating Token Index: 514

Text #19

Max Range: 5.9620. Min Range: -5.9620

Max Act: 5.3699. Min Act: -0.1700

Data Index: 6756489 (Open Web Text)

Max Activating Token Index: 829