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

Dataset: Open Web Text

Neuron 2974 in Layer 6

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: 4.6212. Min Range: -4.6212

Max Act: 4.6212. Min Act: -0.1700

Data Index: 8537253 (Open Web Text)

Max Activating Token Index: 238

Text #1

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.6038. Min Act: -0.1700

Data Index: 7426287 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.5824. Min Act: -0.1700

Data Index: 371077 (Open Web Text)

Max Activating Token Index: 209

Text #3

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.5381. Min Act: -0.1700

Data Index: 3927323 (Open Web Text)

Max Activating Token Index: 907

Text #4

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.5151. Min Act: -0.1700

Data Index: 5777982 (Open Web Text)

Max Activating Token Index: 849

Text #5

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.5385. Min Act: -0.1700

Data Index: 3255352 (Open Web Text)

Max Activating Token Index: 76

Text #6

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.5025. Min Act: -0.1700

Data Index: 1230469 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.5041. Min Act: -0.1700

Data Index: 5487510 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.5192. Min Act: -0.1700

Data Index: 1348412 (Open Web Text)

Max Activating Token Index: 780

Text #9

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.4692. Min Act: -0.1700

Data Index: 6786157 (Open Web Text)

Max Activating Token Index: 596

Text #10

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.4939. Min Act: -0.1700

Data Index: 5393328 (Open Web Text)

Max Activating Token Index: 688

Text #11

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.4711. Min Act: -0.1700

Data Index: 5737925 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.4978. Min Act: -0.1700

Data Index: 3157595 (Open Web Text)

Max Activating Token Index: 757

Text #13

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.4377. Min Act: -0.1700

Data Index: 1035241 (Open Web Text)

Max Activating Token Index: 251

Text #14

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.4712. Min Act: -0.1700

Data Index: 387881 (Open Web Text)

Max Activating Token Index: 662

Text #15

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.4625. Min Act: -0.1700

Data Index: 8630940 (Open Web Text)

Max Activating Token Index: 613

Text #16

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.4637. Min Act: -0.1700

Data Index: 2573892 (Open Web Text)

Max Activating Token Index: 443

Text #17

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.4510. Min Act: -0.1700

Data Index: 3619976 (Open Web Text)

Max Activating Token Index: 303

Text #18

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.4563. Min Act: -0.1700

Data Index: 267505 (Open Web Text)

Max Activating Token Index: 143

Text #19

Max Range: 4.6212. Min Range: -4.6212

Max Act: 4.4284. Min Act: -0.1700

Data Index: 5955226 (Open Web Text)

Max Activating Token Index: 243