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

Dataset: Open Web Text

Neuron 2655 in Layer 5

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: 2.2775. Min Range: -2.2775

Max Act: 2.2698. Min Act: -0.1700

Data Index: 6765668 (Open Web Text)

Max Activating Token Index: 538

Text #1

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2650. Min Act: -0.1700

Data Index: 7655862 (Open Web Text)

Max Activating Token Index: 194

Text #2

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2775. Min Act: -0.1700

Data Index: 4209770 (Open Web Text)

Max Activating Token Index: 80

Text #3

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2697. Min Act: -0.1700

Data Index: 4783418 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2491. Min Act: -0.1700

Data Index: 4267781 (Open Web Text)

Max Activating Token Index: 858

Text #5

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2365. Min Act: -0.1700

Data Index: 3781379 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2468. Min Act: -0.1700

Data Index: 3805299 (Open Web Text)

Max Activating Token Index: 505

Text #7

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2084. Min Act: -0.1700

Data Index: 1968108 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2096. Min Act: -0.1700

Data Index: 5590391 (Open Web Text)

Max Activating Token Index: 228

Text #9

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2060. Min Act: -0.1700

Data Index: 8132931 (Open Web Text)

Max Activating Token Index: 253

Text #10

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2118. Min Act: -0.1700

Data Index: 5359907 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2270. Min Act: -0.1700

Data Index: 2665042 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2002. Min Act: -0.1700

Data Index: 6241440 (Open Web Text)

Max Activating Token Index: 962

Text #13

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2151. Min Act: -0.1700

Data Index: 2742007 (Open Web Text)

Max Activating Token Index: 80

Text #14

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.1923. Min Act: -0.1700

Data Index: 1535026 (Open Web Text)

Max Activating Token Index: 553

Text #15

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.1906. Min Act: -0.1700

Data Index: 4569117 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.1882. Min Act: -0.1700

Data Index: 486723 (Open Web Text)

Max Activating Token Index: 63

Text #17

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.1938. Min Act: -0.1700

Data Index: 4308045 (Open Web Text)

Max Activating Token Index: 874

Text #18

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.2000. Min Act: -0.1700

Data Index: 5943852 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 2.2775. Min Range: -2.2775

Max Act: 2.1882. Min Act: -0.1700

Data Index: 200658 (Open Web Text)

Max Activating Token Index: 164