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

Dataset: Open Web Text

Neuron 2975 in Layer 4

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: 3.0626. Min Range: -3.0626

Max Act: 3.0496. Min Act: -0.1700

Data Index: 5242807 (Open Web Text)

Max Activating Token Index: 562

Text #1

Max Range: 3.0626. Min Range: -3.0626

Max Act: 3.0626. Min Act: -0.1700

Data Index: 7118113 (Open Web Text)

Max Activating Token Index: 197

Text #2

Max Range: 3.0626. Min Range: -3.0626

Max Act: 3.0332. Min Act: -0.1700

Data Index: 5858566 (Open Web Text)

Max Activating Token Index: 230

Text #3

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9981. Min Act: -0.1700

Data Index: 261907 (Open Web Text)

Max Activating Token Index: 413

Text #4

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9974. Min Act: -0.1700

Data Index: 6919656 (Open Web Text)

Max Activating Token Index: 266

Text #5

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9964. Min Act: -0.1700

Data Index: 5675679 (Open Web Text)

Max Activating Token Index: 361

Text #6

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9708. Min Act: -0.1700

Data Index: 5050033 (Open Web Text)

Max Activating Token Index: 760

Text #7

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9593. Min Act: -0.1700

Data Index: 6566432 (Open Web Text)

Max Activating Token Index: 1000

Text #8

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9777. Min Act: -0.1700

Data Index: 4572872 (Open Web Text)

Max Activating Token Index: 231

Text #9

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9765. Min Act: -0.1700

Data Index: 3484673 (Open Web Text)

Max Activating Token Index: 88

Text #10

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9621. Min Act: -0.1700

Data Index: 5808739 (Open Web Text)

Max Activating Token Index: 563

Text #11

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9544. Min Act: -0.1700

Data Index: 4242271 (Open Web Text)

Max Activating Token Index: 964

Text #12

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9664. Min Act: -0.1700

Data Index: 6646050 (Open Web Text)

Max Activating Token Index: 261

Text #13

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9545. Min Act: -0.1700

Data Index: 1465681 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9563. Min Act: -0.1700

Data Index: 6673977 (Open Web Text)

Max Activating Token Index: 328

Text #15

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9508. Min Act: -0.1700

Data Index: 3072354 (Open Web Text)

Max Activating Token Index: 410

Text #16

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9430. Min Act: -0.1700

Data Index: 4201968 (Open Web Text)

Max Activating Token Index: 810

Text #17

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9408. Min Act: -0.1700

Data Index: 534666 (Open Web Text)

Max Activating Token Index: 68

Text #18

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9380. Min Act: -0.1700

Data Index: 3562866 (Open Web Text)

Max Activating Token Index: 945

Text #19

Max Range: 3.0626. Min Range: -3.0626

Max Act: 2.9512. Min Act: -0.1700

Data Index: 91289 (Open Web Text)

Max Activating Token Index: 401