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

Dataset: Open Web Text

Neuron 2015 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: 4.2028. Min Range: -4.2028

Max Act: 4.2028. Min Act: -0.1700

Data Index: 5047754 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.1938. Min Act: -0.1700

Data Index: 5547054 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.1623. Min Act: -0.1700

Data Index: 1726711 (Open Web Text)

Max Activating Token Index: 669

Text #3

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.0853. Min Act: -0.1700

Data Index: 6215074 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.0778. Min Act: -0.1700

Data Index: 4517801 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.0616. Min Act: -0.1700

Data Index: 1822774 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.0498. Min Act: -0.1700

Data Index: 6326260 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.0314. Min Act: -0.1700

Data Index: 4376625 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.0482. Min Act: -0.1700

Data Index: 7208291 (Open Web Text)

Max Activating Token Index: 743

Text #9

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.0018. Min Act: -0.1700

Data Index: 6116668 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.0039. Min Act: -0.1700

Data Index: 618094 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.0232. Min Act: -0.1700

Data Index: 1386238 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.0242. Min Act: -0.1700

Data Index: 1678335 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.2028. Min Range: -4.2028

Max Act: 4.0053. Min Act: -0.1700

Data Index: 1111221 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.2028. Min Range: -4.2028

Max Act: 3.9965. Min Act: -0.1700

Data Index: 6860505 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.2028. Min Range: -4.2028

Max Act: 3.9775. Min Act: -0.1700

Data Index: 6040545 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.2028. Min Range: -4.2028

Max Act: 3.9651. Min Act: -0.1700

Data Index: 6245290 (Open Web Text)

Max Activating Token Index: 909

Text #17

Max Range: 4.2028. Min Range: -4.2028

Max Act: 3.9727. Min Act: -0.1700

Data Index: 5358924 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 4.2028. Min Range: -4.2028

Max Act: 3.9770. Min Act: -0.1700

Data Index: 803849 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.2028. Min Range: -4.2028

Max Act: 3.9728. Min Act: -0.1700

Data Index: 8301967 (Open Web Text)

Max Activating Token Index: 13