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

Dataset: Open Web Text

Neuron 1265 in Layer 2

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: 4.1162. Min Range: -4.1162

Max Act: 4.1162. Min Act: -0.1700

Data Index: 5129056 (Open Web Text)

Max Activating Token Index: 101

Text #1

Max Range: 4.1162. Min Range: -4.1162

Max Act: 4.0095. Min Act: -0.1700

Data Index: 5496044 (Open Web Text)

Max Activating Token Index: 1007

Text #2

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9844. Min Act: -0.1700

Data Index: 8393928 (Open Web Text)

Max Activating Token Index: 962

Text #3

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.9003. Min Act: -0.1700

Data Index: 3820337 (Open Web Text)

Max Activating Token Index: 390

Text #4

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8917. Min Act: -0.1700

Data Index: 8715553 (Open Web Text)

Max Activating Token Index: 425

Text #5

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8638. Min Act: -0.1700

Data Index: 5424706 (Open Web Text)

Max Activating Token Index: 756

Text #6

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8842. Min Act: -0.1700

Data Index: 2939423 (Open Web Text)

Max Activating Token Index: 563

Text #7

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8655. Min Act: -0.1700

Data Index: 6427632 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8652. Min Act: -0.1700

Data Index: 2831748 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8515. Min Act: -0.1700

Data Index: 482281 (Open Web Text)

Max Activating Token Index: 836

Text #10

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8475. Min Act: -0.1700

Data Index: 114199 (Open Web Text)

Max Activating Token Index: 306

Text #11

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8386. Min Act: -0.1700

Data Index: 6776292 (Open Web Text)

Max Activating Token Index: 982

Text #12

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8340. Min Act: -0.1700

Data Index: 514836 (Open Web Text)

Max Activating Token Index: 153

Text #13

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8516. Min Act: -0.1700

Data Index: 3016427 (Open Web Text)

Max Activating Token Index: 403

Text #14

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8566. Min Act: -0.1700

Data Index: 90572 (Open Web Text)

Max Activating Token Index: 408

Text #15

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8528. Min Act: -0.1700

Data Index: 29189 (Open Web Text)

Max Activating Token Index: 249

Text #16

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8337. Min Act: -0.1700

Data Index: 2571205 (Open Web Text)

Max Activating Token Index: 388

Text #17

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8625. Min Act: -0.1700

Data Index: 5609319 (Open Web Text)

Max Activating Token Index: 652

Text #18

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8313. Min Act: -0.1700

Data Index: 1522887 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 4.1162. Min Range: -4.1162

Max Act: 3.8064. Min Act: -0.1700

Data Index: 1071542 (Open Web Text)

Max Activating Token Index: 586