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

Dataset: Open Web Text

Neuron 222 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: 3.3670. Min Range: -3.3670

Max Act: 3.3587. Min Act: -0.1700

Data Index: 6763930 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3670. Min Act: -0.1700

Data Index: 5585627 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3518. Min Act: -0.1700

Data Index: 641896 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3474. Min Act: -0.1700

Data Index: 836258 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3532. Min Act: -0.1700

Data Index: 1330198 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3537. Min Act: -0.1700

Data Index: 1285109 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3611. Min Act: -0.1700

Data Index: 6961658 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3405. Min Act: -0.1700

Data Index: 4147240 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3325. Min Act: -0.1700

Data Index: 229025 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3315. Min Act: -0.1700

Data Index: 4583081 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3270. Min Act: -0.1700

Data Index: 886915 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3163. Min Act: -0.1700

Data Index: 7737689 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3187. Min Act: -0.1700

Data Index: 1897743 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3164. Min Act: -0.1700

Data Index: 3787494 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3205. Min Act: -0.1700

Data Index: 4473763 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3185. Min Act: -0.1700

Data Index: 6091854 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3304. Min Act: -0.1700

Data Index: 6727815 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3131. Min Act: -0.1700

Data Index: 6348004 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3033. Min Act: -0.1700

Data Index: 3784034 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.3670. Min Range: -3.3670

Max Act: 3.3067. Min Act: -0.1700

Data Index: 2661920 (Open Web Text)

Max Activating Token Index: 3