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

Dataset: Open Web Text

Neuron 1685 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: 3.5865. Min Range: -3.5865

Max Act: 3.5865. Min Act: -0.1700

Data Index: 4604858 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.5656. Min Act: -0.1700

Data Index: 4647358 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.5128. Min Act: -0.1700

Data Index: 3899833 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.5131. Min Act: -0.1700

Data Index: 1352585 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4938. Min Act: -0.1700

Data Index: 7197329 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4878. Min Act: -0.1700

Data Index: 7527060 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4951. Min Act: -0.1700

Data Index: 4268852 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4854. Min Act: -0.1700

Data Index: 7559516 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4904. Min Act: -0.1700

Data Index: 6348691 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4703. Min Act: -0.1700

Data Index: 5682439 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.5041. Min Act: -0.1700

Data Index: 861600 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4961. Min Act: -0.1700

Data Index: 2893337 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4464. Min Act: -0.1700

Data Index: 3277765 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4487. Min Act: -0.1700

Data Index: 1629250 (Open Web Text)

Max Activating Token Index: 9

Text #14

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4612. Min Act: -0.1700

Data Index: 2946911 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4533. Min Act: -0.1700

Data Index: 5611455 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4728. Min Act: -0.1700

Data Index: 5394607 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4401. Min Act: -0.1700

Data Index: 1304289 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4632. Min Act: -0.1700

Data Index: 710854 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.5865. Min Range: -3.5865

Max Act: 3.4497. Min Act: -0.1700

Data Index: 4622769 (Open Web Text)

Max Activating Token Index: 4