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

Dataset: Open Web Text

Neuron 2220 in Layer 1

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: 5.9529. Min Range: -5.9529

Max Act: 5.9529. Min Act: -0.1700

Data Index: 1575109 (Open Web Text)

Max Activating Token Index: 700

Text #1

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.9220. Min Act: -0.1700

Data Index: 2327625 (Open Web Text)

Max Activating Token Index: 83

Text #2

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.9194. Min Act: -0.1699

Data Index: 6057537 (Open Web Text)

Max Activating Token Index: 91

Text #3

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.8599. Min Act: -0.1700

Data Index: 2572784 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.7739. Min Act: -0.1700

Data Index: 5174588 (Open Web Text)

Max Activating Token Index: 78

Text #5

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.7756. Min Act: -0.1700

Data Index: 6218251 (Open Web Text)

Max Activating Token Index: 76

Text #6

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.7740. Min Act: -0.1700

Data Index: 5189913 (Open Web Text)

Max Activating Token Index: 121

Text #7

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6961. Min Act: -0.1698

Data Index: 6441857 (Open Web Text)

Max Activating Token Index: 74

Text #8

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6690. Min Act: -0.1700

Data Index: 1396088 (Open Web Text)

Max Activating Token Index: 182

Text #9

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6874. Min Act: -0.1700

Data Index: 3771517 (Open Web Text)

Max Activating Token Index: 204

Text #10

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6804. Min Act: -0.1700

Data Index: 6928647 (Open Web Text)

Max Activating Token Index: 136

Text #11

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6404. Min Act: -0.1700

Data Index: 7078954 (Open Web Text)

Max Activating Token Index: 97

Text #12

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6750. Min Act: -0.1700

Data Index: 1356634 (Open Web Text)

Max Activating Token Index: 284

Text #13

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6625. Min Act: -0.1699

Data Index: 322012 (Open Web Text)

Max Activating Token Index: 123

Text #14

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6090. Min Act: -0.1700

Data Index: 6140102 (Open Web Text)

Max Activating Token Index: 102

Text #15

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6585. Min Act: -0.1700

Data Index: 7562246 (Open Web Text)

Max Activating Token Index: 129

Text #16

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6431. Min Act: -0.1700

Data Index: 8319619 (Open Web Text)

Max Activating Token Index: 57

Text #17

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6112. Min Act: -0.1700

Data Index: 3792293 (Open Web Text)

Max Activating Token Index: 251

Text #18

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6019. Min Act: -0.1700

Data Index: 3745454 (Open Web Text)

Max Activating Token Index: 449

Text #19

Max Range: 5.9529. Min Range: -5.9529

Max Act: 5.6351. Min Act: -0.1700

Data Index: 1748528 (Open Web Text)

Max Activating Token Index: 63