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

Dataset: Open Web Text

Neuron 962 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: 4.5880. Min Range: -4.5880

Max Act: 4.5880. Min Act: -0.1700

Data Index: 1238956 (Open Web Text)

Max Activating Token Index: 541

Text #1

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.5320. Min Act: -0.1700

Data Index: 3520520 (Open Web Text)

Max Activating Token Index: 120

Text #2

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4717. Min Act: -0.1700

Data Index: 5697482 (Open Web Text)

Max Activating Token Index: 755

Text #3

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4492. Min Act: -0.1700

Data Index: 6616974 (Open Web Text)

Max Activating Token Index: 810

Text #4

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.5162. Min Act: -0.1700

Data Index: 6940911 (Open Web Text)

Max Activating Token Index: 352

Text #5

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4033. Min Act: -0.1700

Data Index: 3404100 (Open Web Text)

Max Activating Token Index: 445

Text #6

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.5325. Min Act: -0.1700

Data Index: 6985581 (Open Web Text)

Max Activating Token Index: 567

Text #7

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4393. Min Act: -0.1700

Data Index: 4260689 (Open Web Text)

Max Activating Token Index: 950

Text #8

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4317. Min Act: -0.1700

Data Index: 2287809 (Open Web Text)

Max Activating Token Index: 473

Text #9

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4254. Min Act: -0.1700

Data Index: 8571521 (Open Web Text)

Max Activating Token Index: 307

Text #10

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4337. Min Act: -0.1700

Data Index: 1482385 (Open Web Text)

Max Activating Token Index: 255

Text #11

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.3967. Min Act: -0.1700

Data Index: 4830530 (Open Web Text)

Max Activating Token Index: 268

Text #12

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.3823. Min Act: -0.1700

Data Index: 6522157 (Open Web Text)

Max Activating Token Index: 558

Text #13

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4295. Min Act: -0.1700

Data Index: 8152179 (Open Web Text)

Max Activating Token Index: 783

Text #14

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4056. Min Act: -0.1700

Data Index: 6158266 (Open Web Text)

Max Activating Token Index: 626

Text #15

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.3639. Min Act: -0.1700

Data Index: 7528739 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.3646. Min Act: -0.1700

Data Index: 586250 (Open Web Text)

Max Activating Token Index: 450

Text #17

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4162. Min Act: -0.1700

Data Index: 5590615 (Open Web Text)

Max Activating Token Index: 561

Text #18

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.4118. Min Act: -0.1700

Data Index: 7373495 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 4.5880. Min Range: -4.5880

Max Act: 4.3754. Min Act: -0.1700

Data Index: 2013012 (Open Web Text)

Max Activating Token Index: 330