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

Dataset: Open Web Text

Neuron 1845 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: 2.4943. Min Range: -2.4943

Max Act: 2.4943. Min Act: -0.1700

Data Index: 890458 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.4111. Min Act: -0.1700

Data Index: 8594426 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.3431. Min Act: -0.1700

Data Index: 8380691 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.1602. Min Act: -0.1700

Data Index: 7219324 (Open Web Text)

Max Activating Token Index: 211

Text #4

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.1579. Min Act: -0.1700

Data Index: 1766631 (Open Web Text)

Max Activating Token Index: 271

Text #5

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.1582. Min Act: -0.1700

Data Index: 478339 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.1377. Min Act: -0.1700

Data Index: 1516170 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.1204. Min Act: -0.1700

Data Index: 7748678 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.1161. Min Act: -0.1700

Data Index: 989136 (Open Web Text)

Max Activating Token Index: 105

Text #9

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.1102. Min Act: -0.1700

Data Index: 5376742 (Open Web Text)

Max Activating Token Index: 514

Text #10

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.0886. Min Act: -0.1699

Data Index: 8748779 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.0912. Min Act: -0.1700

Data Index: 1747517 (Open Web Text)

Max Activating Token Index: 106

Text #12

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.0769. Min Act: -0.1700

Data Index: 2129097 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.0774. Min Act: -0.1700

Data Index: 2857240 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.0677. Min Act: -0.1700

Data Index: 3866528 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.0709. Min Act: -0.1700

Data Index: 7377131 (Open Web Text)

Max Activating Token Index: 324

Text #16

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.0682. Min Act: -0.1700

Data Index: 4835660 (Open Web Text)

Max Activating Token Index: 529

Text #17

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.0485. Min Act: -0.1700

Data Index: 2173860 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.0390. Min Act: -0.1700

Data Index: 6322039 (Open Web Text)

Max Activating Token Index: 185

Text #19

Max Range: 2.4943. Min Range: -2.4943

Max Act: 2.0446. Min Act: -0.1700

Data Index: 4623746 (Open Web Text)

Max Activating Token Index: 120