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

Dataset: Open Web Text

Neuron 1218 in Layer 0

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: 5.6581. Min Range: -5.6581

Max Act: 5.6323. Min Act: -0.1700

Data Index: 1118750 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.6309. Min Act: -0.1700

Data Index: 6759611 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.6581. Min Act: -0.1700

Data Index: 1634363 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.5589. Min Act: -0.1700

Data Index: 659523 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.5641. Min Act: -0.1700

Data Index: 7834418 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.5756. Min Act: -0.1700

Data Index: 4144939 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.5400. Min Act: -0.1700

Data Index: 6329005 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.5418. Min Act: -0.1700

Data Index: 5186003 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.5141. Min Act: -0.1700

Data Index: 3203689 (Open Web Text)

Max Activating Token Index: 105

Text #9

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.5015. Min Act: -0.1700

Data Index: 6307457 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.5209. Min Act: -0.1700

Data Index: 586519 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.4850. Min Act: -0.1700

Data Index: 7600018 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.4851. Min Act: -0.1700

Data Index: 5699237 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.4850. Min Act: -0.1700

Data Index: 478560 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.4850. Min Act: -0.1700

Data Index: 35830 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.4887. Min Act: -0.1700

Data Index: 3396470 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.4413. Min Act: -0.1700

Data Index: 3346144 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.4443. Min Act: -0.1700

Data Index: 5257906 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.4346. Min Act: -0.1700

Data Index: 3517643 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.4664. Min Act: -0.1700

Data Index: 3593463 (Open Web Text)

Max Activating Token Index: 105