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

Dataset: Open Web Text

Neuron 1488 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: 2.9209. Min Range: -2.9209

Max Act: 2.9209. Min Act: -0.1700

Data Index: 3842766 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.9064. Min Act: -0.1700

Data Index: 6535346 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.8680. Min Act: -0.1700

Data Index: 1070206 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.8674. Min Act: -0.1700

Data Index: 8615734 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.8052. Min Act: -0.1700

Data Index: 6200554 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.7966. Min Act: -0.1700

Data Index: 8700814 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.7889. Min Act: -0.1700

Data Index: 1834543 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.7127. Min Act: -0.1700

Data Index: 2106144 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.7064. Min Act: -0.1700

Data Index: 8023154 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6931. Min Act: -0.1700

Data Index: 120350 (Open Web Text)

Max Activating Token Index: 338

Text #10

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6709. Min Act: -0.1700

Data Index: 3294917 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6703. Min Act: -0.1700

Data Index: 6658545 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6748. Min Act: -0.1700

Data Index: 1618284 (Open Web Text)

Max Activating Token Index: 692

Text #13

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6681. Min Act: -0.1700

Data Index: 7301466 (Open Web Text)

Max Activating Token Index: 646

Text #14

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6557. Min Act: -0.1700

Data Index: 3419219 (Open Web Text)

Max Activating Token Index: 589

Text #15

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6441. Min Act: -0.1700

Data Index: 906912 (Open Web Text)

Max Activating Token Index: 692

Text #16

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6400. Min Act: -0.1700

Data Index: 7643740 (Open Web Text)

Max Activating Token Index: 69

Text #17

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6113. Min Act: -0.1700

Data Index: 5081580 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6347. Min Act: -0.1700

Data Index: 2121043 (Open Web Text)

Max Activating Token Index: 695

Text #19

Max Range: 2.9209. Min Range: -2.9209

Max Act: 2.6169. Min Act: -0.1700

Data Index: 5613395 (Open Web Text)

Max Activating Token Index: 813