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

Dataset: Open Web Text

Neuron 2716 in Layer 0

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: 2.4289. Min Range: -2.4289

Max Act: 2.4289. Min Act: -0.1700

Data Index: 1727927 (Open Web Text)

Max Activating Token Index: 10

Text #1

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.4226. Min Act: -0.1700

Data Index: 6310745 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3938. Min Act: -0.1700

Data Index: 8780078 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3783. Min Act: -0.1700

Data Index: 3523954 (Open Web Text)

Max Activating Token Index: 73

Text #4

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3611. Min Act: -0.1700

Data Index: 2649388 (Open Web Text)

Max Activating Token Index: 247

Text #5

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3442. Min Act: -0.1700

Data Index: 6823317 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3375. Min Act: -0.1700

Data Index: 7862136 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3261. Min Act: -0.1700

Data Index: 6459161 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3282. Min Act: -0.1700

Data Index: 4352020 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3310. Min Act: -0.1700

Data Index: 3523939 (Open Web Text)

Max Activating Token Index: 210

Text #10

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3243. Min Act: -0.1700

Data Index: 1247173 (Open Web Text)

Max Activating Token Index: 176

Text #11

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3347. Min Act: -0.1700

Data Index: 6211624 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3313. Min Act: -0.1700

Data Index: 5095385 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3227. Min Act: -0.1700

Data Index: 4676875 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3126. Min Act: -0.1700

Data Index: 2287293 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3101. Min Act: -0.1700

Data Index: 6115344 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3106. Min Act: -0.1700

Data Index: 343452 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3053. Min Act: -0.1700

Data Index: 4073331 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3065. Min Act: -0.1700

Data Index: 477634 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 2.4289. Min Range: -2.4289

Max Act: 2.3090. Min Act: -0.1700

Data Index: 6705091 (Open Web Text)

Max Activating Token Index: 476