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

Dataset: Open Web Text

Neuron 563 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: 3.2875. Min Range: -3.2875

Max Act: 3.2875. Min Act: -0.1700

Data Index: 6451978 (Open Web Text)

Max Activating Token Index: 236

Text #1

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.2047. Min Act: -0.1700

Data Index: 3769778 (Open Web Text)

Max Activating Token Index: 756

Text #2

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.2107. Min Act: -0.1700

Data Index: 2492448 (Open Web Text)

Max Activating Token Index: 253

Text #3

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1715. Min Act: -0.1700

Data Index: 6065919 (Open Web Text)

Max Activating Token Index: 47

Text #4

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1537. Min Act: -0.1700

Data Index: 8500546 (Open Web Text)

Max Activating Token Index: 117

Text #5

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1264. Min Act: -0.1700

Data Index: 8233303 (Open Web Text)

Max Activating Token Index: 138

Text #6

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1160. Min Act: -0.1700

Data Index: 5106506 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1152. Min Act: -0.1700

Data Index: 2774688 (Open Web Text)

Max Activating Token Index: 356

Text #8

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1563. Min Act: -0.1700

Data Index: 1756199 (Open Web Text)

Max Activating Token Index: 191

Text #9

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1387. Min Act: -0.1700

Data Index: 7711400 (Open Web Text)

Max Activating Token Index: 780

Text #10

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1097. Min Act: -0.1700

Data Index: 1027062 (Open Web Text)

Max Activating Token Index: 262

Text #11

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.0947. Min Act: -0.1700

Data Index: 556243 (Open Web Text)

Max Activating Token Index: 157

Text #12

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.0787. Min Act: -0.1700

Data Index: 1778571 (Open Web Text)

Max Activating Token Index: 507

Text #13

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.0886. Min Act: -0.1700

Data Index: 8691187 (Open Web Text)

Max Activating Token Index: 329

Text #14

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.0840. Min Act: -0.1700

Data Index: 7527600 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.1071. Min Act: -0.1700

Data Index: 1326927 (Open Web Text)

Max Activating Token Index: 560

Text #16

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.0695. Min Act: -0.1700

Data Index: 6096805 (Open Web Text)

Max Activating Token Index: 749

Text #17

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.0526. Min Act: -0.1700

Data Index: 4521407 (Open Web Text)

Max Activating Token Index: 387

Text #18

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.0709. Min Act: -0.1700

Data Index: 5181831 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 3.2875. Min Range: -3.2875

Max Act: 3.0481. Min Act: -0.1700

Data Index: 3932462 (Open Web Text)

Max Activating Token Index: 945