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

Dataset: Open Web Text

Neuron 963 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: 3.8242. Min Range: -3.8242

Max Act: 3.8242. Min Act: -0.1700

Data Index: 5952581 (Open Web Text)

Max Activating Token Index: 377

Text #1

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7660. Min Act: -0.1700

Data Index: 3005985 (Open Web Text)

Max Activating Token Index: 923

Text #2

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7247. Min Act: -0.1700

Data Index: 8760820 (Open Web Text)

Max Activating Token Index: 944

Text #3

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7603. Min Act: -0.1700

Data Index: 6651570 (Open Web Text)

Max Activating Token Index: 469

Text #4

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7401. Min Act: -0.1700

Data Index: 5820196 (Open Web Text)

Max Activating Token Index: 987

Text #5

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7385. Min Act: -0.1700

Data Index: 7653278 (Open Web Text)

Max Activating Token Index: 884

Text #6

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6974. Min Act: -0.1700

Data Index: 3287955 (Open Web Text)

Max Activating Token Index: 79

Text #7

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7183. Min Act: -0.1700

Data Index: 4512545 (Open Web Text)

Max Activating Token Index: 998

Text #8

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7138. Min Act: -0.1700

Data Index: 4179684 (Open Web Text)

Max Activating Token Index: 408

Text #9

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6970. Min Act: -0.1700

Data Index: 2911813 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6579. Min Act: -0.1700

Data Index: 2847260 (Open Web Text)

Max Activating Token Index: 817

Text #11

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6944. Min Act: -0.1700

Data Index: 2785248 (Open Web Text)

Max Activating Token Index: 571

Text #12

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7092. Min Act: -0.1700

Data Index: 6204625 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7255. Min Act: -0.1700

Data Index: 8710417 (Open Web Text)

Max Activating Token Index: 434

Text #14

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6861. Min Act: -0.1700

Data Index: 8422475 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6911. Min Act: -0.1700

Data Index: 8346613 (Open Web Text)

Max Activating Token Index: 69

Text #16

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.7137. Min Act: -0.1700

Data Index: 8045841 (Open Web Text)

Max Activating Token Index: 381

Text #17

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6573. Min Act: -0.1700

Data Index: 7763040 (Open Web Text)

Max Activating Token Index: 717

Text #18

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6578. Min Act: -0.1700

Data Index: 7061012 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 3.8242. Min Range: -3.8242

Max Act: 3.6646. Min Act: -0.1700

Data Index: 6323026 (Open Web Text)

Max Activating Token Index: 110