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

Dataset: Open Web Text

Neuron 625 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: 4.2961. Min Range: -4.2961

Max Act: 4.2961. Min Act: -0.1700

Data Index: 8468679 (Open Web Text)

Max Activating Token Index: 584

Text #1

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.2451. Min Act: -0.1700

Data Index: 6616050 (Open Web Text)

Max Activating Token Index: 61

Text #2

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1380. Min Act: -0.1700

Data Index: 7907637 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1321. Min Act: -0.1700

Data Index: 4210210 (Open Web Text)

Max Activating Token Index: 860

Text #4

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.2180. Min Act: -0.1700

Data Index: 5262657 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1427. Min Act: -0.1700

Data Index: 4485148 (Open Web Text)

Max Activating Token Index: 675

Text #6

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.1306. Min Act: -0.1700

Data Index: 3166039 (Open Web Text)

Max Activating Token Index: 692

Text #7

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.0926. Min Act: -0.1700

Data Index: 1774041 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.0776. Min Act: -0.1700

Data Index: 5343753 (Open Web Text)

Max Activating Token Index: 119

Text #9

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.0761. Min Act: -0.1700

Data Index: 3861292 (Open Web Text)

Max Activating Token Index: 835

Text #10

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.0591. Min Act: -0.1700

Data Index: 6765116 (Open Web Text)

Max Activating Token Index: 417

Text #11

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.0196. Min Act: -0.1700

Data Index: 8753821 (Open Web Text)

Max Activating Token Index: 42

Text #12

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.0285. Min Act: -0.1700

Data Index: 3095708 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.0390. Min Act: -0.1700

Data Index: 2618531 (Open Web Text)

Max Activating Token Index: 886

Text #14

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.0292. Min Act: -0.1700

Data Index: 2072250 (Open Web Text)

Max Activating Token Index: 899

Text #15

Max Range: 4.2961. Min Range: -4.2961

Max Act: 4.0381. Min Act: -0.1700

Data Index: 1552919 (Open Web Text)

Max Activating Token Index: 179

Text #16

Max Range: 4.2961. Min Range: -4.2961

Max Act: 3.9335. Min Act: -0.1700

Data Index: 8050095 (Open Web Text)

Max Activating Token Index: 575

Text #17

Max Range: 4.2961. Min Range: -4.2961

Max Act: 3.9759. Min Act: -0.1700

Data Index: 7918066 (Open Web Text)

Max Activating Token Index: 169

Text #18

Max Range: 4.2961. Min Range: -4.2961

Max Act: 3.9341. Min Act: -0.1700

Data Index: 460501 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 4.2961. Min Range: -4.2961

Max Act: 3.9396. Min Act: -0.1700

Data Index: 8034376 (Open Web Text)

Max Activating Token Index: 986