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

Dataset: Open Web Text

Neuron 438 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: 3.4640. Min Range: -3.4640

Max Act: 3.4640. Min Act: -0.1700

Data Index: 7406628 (Open Web Text)

Max Activating Token Index: 1013

Text #1

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.3696. Min Act: -0.1700

Data Index: 528538 (Open Web Text)

Max Activating Token Index: 477

Text #2

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.3556. Min Act: -0.1700

Data Index: 1325528 (Open Web Text)

Max Activating Token Index: 982

Text #3

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.3254. Min Act: -0.1700

Data Index: 2295701 (Open Web Text)

Max Activating Token Index: 810

Text #4

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.3081. Min Act: -0.1700

Data Index: 6106675 (Open Web Text)

Max Activating Token Index: 93

Text #5

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.2922. Min Act: -0.1700

Data Index: 3603656 (Open Web Text)

Max Activating Token Index: 1013

Text #6

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.2708. Min Act: -0.1700

Data Index: 8148471 (Open Web Text)

Max Activating Token Index: 791

Text #7

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.2336. Min Act: -0.1700

Data Index: 7491674 (Open Web Text)

Max Activating Token Index: 677

Text #8

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.2549. Min Act: -0.1700

Data Index: 4449480 (Open Web Text)

Max Activating Token Index: 398

Text #9

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.2291. Min Act: -0.1700

Data Index: 7589822 (Open Web Text)

Max Activating Token Index: 1018

Text #10

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.2184. Min Act: -0.1700

Data Index: 7669229 (Open Web Text)

Max Activating Token Index: 304

Text #11

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1872. Min Act: -0.1700

Data Index: 7466644 (Open Web Text)

Max Activating Token Index: 112

Text #12

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.2048. Min Act: -0.1700

Data Index: 5573462 (Open Web Text)

Max Activating Token Index: 441

Text #13

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.2212. Min Act: -0.1700

Data Index: 7235164 (Open Web Text)

Max Activating Token Index: 928

Text #14

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1855. Min Act: -0.1700

Data Index: 5846692 (Open Web Text)

Max Activating Token Index: 517

Text #15

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.2195. Min Act: -0.1700

Data Index: 7154685 (Open Web Text)

Max Activating Token Index: 468

Text #16

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1600. Min Act: -0.1700

Data Index: 7338897 (Open Web Text)

Max Activating Token Index: 829

Text #17

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1757. Min Act: -0.1700

Data Index: 3254152 (Open Web Text)

Max Activating Token Index: 947

Text #18

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1782. Min Act: -0.1700

Data Index: 752529 (Open Web Text)

Max Activating Token Index: 554

Text #19

Max Range: 3.4640. Min Range: -3.4640

Max Act: 3.1565. Min Act: -0.1700

Data Index: 4460395 (Open Web Text)

Max Activating Token Index: 966