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

Dataset: Open Web Text

Neuron 2777 in Layer 4

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: 4.2510. Min Range: -4.2510

Max Act: 4.2510. Min Act: -0.1700

Data Index: 6778163 (Open Web Text)

Max Activating Token Index: 63

Text #1

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.1706. Min Act: -0.1700

Data Index: 7804984 (Open Web Text)

Max Activating Token Index: 132

Text #2

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.1590. Min Act: -0.1700

Data Index: 527541 (Open Web Text)

Max Activating Token Index: 99

Text #3

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.1359. Min Act: -0.1700

Data Index: 885790 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.1165. Min Act: -0.1700

Data Index: 3222626 (Open Web Text)

Max Activating Token Index: 989

Text #5

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.1087. Min Act: -0.1700

Data Index: 1790269 (Open Web Text)

Max Activating Token Index: 488

Text #6

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.1119. Min Act: -0.1700

Data Index: 6560563 (Open Web Text)

Max Activating Token Index: 275

Text #7

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.0851. Min Act: -0.1700

Data Index: 1032856 (Open Web Text)

Max Activating Token Index: 237

Text #8

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.1271. Min Act: -0.1700

Data Index: 8585467 (Open Web Text)

Max Activating Token Index: 964

Text #9

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.1100. Min Act: -0.1700

Data Index: 3845622 (Open Web Text)

Max Activating Token Index: 1010

Text #10

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.0728. Min Act: -0.1700

Data Index: 7970923 (Open Web Text)

Max Activating Token Index: 472

Text #11

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.0123. Min Act: -0.1700

Data Index: 5037374 (Open Web Text)

Max Activating Token Index: 608

Text #12

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.0236. Min Act: -0.1700

Data Index: 4365706 (Open Web Text)

Max Activating Token Index: 472

Text #13

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.0200. Min Act: -0.1700

Data Index: 2856241 (Open Web Text)

Max Activating Token Index: 836

Text #14

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.0261. Min Act: -0.1700

Data Index: 7534399 (Open Web Text)

Max Activating Token Index: 557

Text #15

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.0333. Min Act: -0.1700

Data Index: 1456879 (Open Web Text)

Max Activating Token Index: 991

Text #16

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.0122. Min Act: -0.1700

Data Index: 6040262 (Open Web Text)

Max Activating Token Index: 712

Text #17

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.9912. Min Act: -0.1700

Data Index: 6859852 (Open Web Text)

Max Activating Token Index: 305

Text #18

Max Range: 4.2510. Min Range: -4.2510

Max Act: 4.0037. Min Act: -0.1700

Data Index: 6025234 (Open Web Text)

Max Activating Token Index: 525

Text #19

Max Range: 4.2510. Min Range: -4.2510

Max Act: 3.9866. Min Act: -0.1700

Data Index: 7356648 (Open Web Text)

Max Activating Token Index: 389