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

Dataset: Open Web Text

Neuron 413 in Layer 2

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: 3.7282. Min Range: -3.7282

Max Act: 3.7282. Min Act: -0.1700

Data Index: 6327965 (Open Web Text)

Max Activating Token Index: 37

Text #1

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.6297. Min Act: -0.1700

Data Index: 6058872 (Open Web Text)

Max Activating Token Index: 67

Text #2

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.6069. Min Act: -0.1700

Data Index: 943978 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5950. Min Act: -0.1700

Data Index: 2670201 (Open Web Text)

Max Activating Token Index: 581

Text #4

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5785. Min Act: -0.1700

Data Index: 1934691 (Open Web Text)

Max Activating Token Index: 717

Text #5

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5888. Min Act: -0.1700

Data Index: 5596280 (Open Web Text)

Max Activating Token Index: 475

Text #6

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5553. Min Act: -0.1700

Data Index: 4362892 (Open Web Text)

Max Activating Token Index: 560

Text #7

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5585. Min Act: -0.1700

Data Index: 4025738 (Open Web Text)

Max Activating Token Index: 909

Text #8

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5366. Min Act: -0.1700

Data Index: 8590019 (Open Web Text)

Max Activating Token Index: 197

Text #9

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5522. Min Act: -0.1700

Data Index: 8065467 (Open Web Text)

Max Activating Token Index: 716

Text #10

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5436. Min Act: -0.1700

Data Index: 7892314 (Open Web Text)

Max Activating Token Index: 243

Text #11

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5537. Min Act: -0.1700

Data Index: 2618668 (Open Web Text)

Max Activating Token Index: 39

Text #12

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5326. Min Act: -0.1700

Data Index: 1424837 (Open Web Text)

Max Activating Token Index: 424

Text #13

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5371. Min Act: -0.1700

Data Index: 2438874 (Open Web Text)

Max Activating Token Index: 60

Text #14

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5534. Min Act: -0.1700

Data Index: 203051 (Open Web Text)

Max Activating Token Index: 160

Text #15

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5108. Min Act: -0.1700

Data Index: 1726600 (Open Web Text)

Max Activating Token Index: 138

Text #16

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5101. Min Act: -0.1700

Data Index: 2882938 (Open Web Text)

Max Activating Token Index: 390

Text #17

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5039. Min Act: -0.1700

Data Index: 3066277 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5260. Min Act: -0.1700

Data Index: 3352065 (Open Web Text)

Max Activating Token Index: 109

Text #19

Max Range: 3.7282. Min Range: -3.7282

Max Act: 3.5352. Min Act: -0.1700

Data Index: 244683 (Open Web Text)

Max Activating Token Index: 394