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

Dataset: Open Web Text

Neuron 2099 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: 4.5575. Min Range: -4.5575

Max Act: 4.5575. Min Act: -0.1700

Data Index: 2394171 (Open Web Text)

Max Activating Token Index: 102

Text #1

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.5020. Min Act: -0.1700

Data Index: 5437466 (Open Web Text)

Max Activating Token Index: 43

Text #2

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.4691. Min Act: -0.1700

Data Index: 5029087 (Open Web Text)

Max Activating Token Index: 669

Text #3

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.4309. Min Act: -0.1700

Data Index: 3526617 (Open Web Text)

Max Activating Token Index: 796

Text #4

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.4596. Min Act: -0.1700

Data Index: 1442383 (Open Web Text)

Max Activating Token Index: 473

Text #5

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.4550. Min Act: -0.1700

Data Index: 3162071 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.4279. Min Act: -0.1700

Data Index: 7768820 (Open Web Text)

Max Activating Token Index: 224

Text #7

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.4348. Min Act: -0.1700

Data Index: 886247 (Open Web Text)

Max Activating Token Index: 185

Text #8

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.4105. Min Act: -0.1700

Data Index: 4764621 (Open Web Text)

Max Activating Token Index: 65

Text #9

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.3977. Min Act: -0.1700

Data Index: 6858098 (Open Web Text)

Max Activating Token Index: 142

Text #10

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.4183. Min Act: -0.1700

Data Index: 1708016 (Open Web Text)

Max Activating Token Index: 631

Text #11

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.3833. Min Act: -0.1700

Data Index: 8439421 (Open Web Text)

Max Activating Token Index: 86

Text #12

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.3766. Min Act: -0.1700

Data Index: 8020782 (Open Web Text)

Max Activating Token Index: 95

Text #13

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.3906. Min Act: -0.1700

Data Index: 7739893 (Open Web Text)

Max Activating Token Index: 426

Text #14

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.3586. Min Act: -0.1700

Data Index: 7616312 (Open Web Text)

Max Activating Token Index: 459

Text #15

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.3672. Min Act: -0.1700

Data Index: 5397779 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.3812. Min Act: -0.1700

Data Index: 5882586 (Open Web Text)

Max Activating Token Index: 367

Text #17

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.3701. Min Act: -0.1700

Data Index: 5179478 (Open Web Text)

Max Activating Token Index: 481

Text #18

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.3285. Min Act: -0.1700

Data Index: 167154 (Open Web Text)

Max Activating Token Index: 75

Text #19

Max Range: 4.5575. Min Range: -4.5575

Max Act: 4.3566. Min Act: -0.1700

Data Index: 1266159 (Open Web Text)

Max Activating Token Index: 578