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

Dataset: Open Web Text

Neuron 1415 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: 6.8864. Min Range: -6.8864

Max Act: 6.8646. Min Act: -0.1700

Data Index: 8254649 (Open Web Text)

Max Activating Token Index: 464

Text #1

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8864. Min Act: -0.1700

Data Index: 7453790 (Open Web Text)

Max Activating Token Index: 434

Text #2

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8263. Min Act: -0.1700

Data Index: 625554 (Open Web Text)

Max Activating Token Index: 374

Text #3

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8396. Min Act: -0.1700

Data Index: 3888006 (Open Web Text)

Max Activating Token Index: 546

Text #4

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8512. Min Act: -0.1700

Data Index: 1136045 (Open Web Text)

Max Activating Token Index: 688

Text #5

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8206. Min Act: -0.1700

Data Index: 2111334 (Open Web Text)

Max Activating Token Index: 382

Text #6

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8301. Min Act: -0.1700

Data Index: 4216966 (Open Web Text)

Max Activating Token Index: 956

Text #7

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8216. Min Act: -0.1700

Data Index: 8822175 (Open Web Text)

Max Activating Token Index: 947

Text #8

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8308. Min Act: -0.1700

Data Index: 3906551 (Open Web Text)

Max Activating Token Index: 527

Text #9

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8240. Min Act: -0.1700

Data Index: 5411608 (Open Web Text)

Max Activating Token Index: 574

Text #10

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.7977. Min Act: -0.1700

Data Index: 5891037 (Open Web Text)

Max Activating Token Index: 259

Text #11

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.7814. Min Act: -0.1700

Data Index: 6326336 (Open Web Text)

Max Activating Token Index: 856

Text #12

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8184. Min Act: -0.1700

Data Index: 2988460 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.7874. Min Act: -0.1700

Data Index: 7073567 (Open Web Text)

Max Activating Token Index: 859

Text #14

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8221. Min Act: -0.1700

Data Index: 5004179 (Open Web Text)

Max Activating Token Index: 947

Text #15

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8105. Min Act: -0.1700

Data Index: 3236999 (Open Web Text)

Max Activating Token Index: 106

Text #16

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.7995. Min Act: -0.1700

Data Index: 7636514 (Open Web Text)

Max Activating Token Index: 426

Text #17

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8089. Min Act: -0.1700

Data Index: 490672 (Open Web Text)

Max Activating Token Index: 854

Text #18

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8205. Min Act: -0.1700

Data Index: 7908218 (Open Web Text)

Max Activating Token Index: 633

Text #19

Max Range: 6.8864. Min Range: -6.8864

Max Act: 6.8086. Min Act: -0.1700

Data Index: 8014736 (Open Web Text)

Max Activating Token Index: 446