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

Dataset: Open Web Text

Neuron 2600 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: 4.7757. Min Range: -4.7757

Max Act: 4.7757. Min Act: -0.1700

Data Index: 8549655 (Open Web Text)

Max Activating Token Index: 841

Text #1

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.7254. Min Act: -0.1700

Data Index: 5505354 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.7349. Min Act: -0.1700

Data Index: 6328862 (Open Web Text)

Max Activating Token Index: 495

Text #3

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.7255. Min Act: -0.1700

Data Index: 2007814 (Open Web Text)

Max Activating Token Index: 817

Text #4

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.7090. Min Act: -0.1700

Data Index: 3423689 (Open Web Text)

Max Activating Token Index: 718

Text #5

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6993. Min Act: -0.1700

Data Index: 2141494 (Open Web Text)

Max Activating Token Index: 485

Text #6

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6546. Min Act: -0.1700

Data Index: 8101281 (Open Web Text)

Max Activating Token Index: 117

Text #7

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6624. Min Act: -0.1700

Data Index: 4639769 (Open Web Text)

Max Activating Token Index: 408

Text #8

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6691. Min Act: -0.1700

Data Index: 891207 (Open Web Text)

Max Activating Token Index: 674

Text #9

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6685. Min Act: -0.1700

Data Index: 4426739 (Open Web Text)

Max Activating Token Index: 981

Text #10

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6180. Min Act: -0.1700

Data Index: 7323257 (Open Web Text)

Max Activating Token Index: 864

Text #11

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6452. Min Act: -0.1700

Data Index: 3439468 (Open Web Text)

Max Activating Token Index: 520

Text #12

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.5998. Min Act: -0.1700

Data Index: 6190117 (Open Web Text)

Max Activating Token Index: 723

Text #13

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6208. Min Act: -0.1700

Data Index: 3108895 (Open Web Text)

Max Activating Token Index: 608

Text #14

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6083. Min Act: -0.1700

Data Index: 2183896 (Open Web Text)

Max Activating Token Index: 368

Text #15

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6023. Min Act: -0.1700

Data Index: 6496489 (Open Web Text)

Max Activating Token Index: 556

Text #16

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.5795. Min Act: -0.1700

Data Index: 7092454 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6007. Min Act: -0.1700

Data Index: 912264 (Open Web Text)

Max Activating Token Index: 967

Text #18

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.6028. Min Act: -0.1700

Data Index: 7575892 (Open Web Text)

Max Activating Token Index: 271

Text #19

Max Range: 4.7757. Min Range: -4.7757

Max Act: 4.5835. Min Act: -0.1700

Data Index: 2269761 (Open Web Text)

Max Activating Token Index: 841