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

Dataset: Open Web Text

Neuron 3017 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: 4.1530. Min Range: -4.1530

Max Act: 4.1530. Min Act: -0.1700

Data Index: 2449907 (Open Web Text)

Max Activating Token Index: 100

Text #1

Max Range: 4.1530. Min Range: -4.1530

Max Act: 4.1165. Min Act: -0.1700

Data Index: 970450 (Open Web Text)

Max Activating Token Index: 847

Text #2

Max Range: 4.1530. Min Range: -4.1530

Max Act: 4.1169. Min Act: -0.1700

Data Index: 3319680 (Open Web Text)

Max Activating Token Index: 1010

Text #3

Max Range: 4.1530. Min Range: -4.1530

Max Act: 4.0476. Min Act: -0.1700

Data Index: 7333008 (Open Web Text)

Max Activating Token Index: 586

Text #4

Max Range: 4.1530. Min Range: -4.1530

Max Act: 4.0644. Min Act: -0.1700

Data Index: 7327054 (Open Web Text)

Max Activating Token Index: 212

Text #5

Max Range: 4.1530. Min Range: -4.1530

Max Act: 4.0349. Min Act: -0.1700

Data Index: 6273613 (Open Web Text)

Max Activating Token Index: 328

Text #6

Max Range: 4.1530. Min Range: -4.1530

Max Act: 4.0383. Min Act: -0.1700

Data Index: 3393911 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 4.1530. Min Range: -4.1530

Max Act: 4.0264. Min Act: -0.1700

Data Index: 4850850 (Open Web Text)

Max Activating Token Index: 668

Text #8

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.9596. Min Act: -0.1700

Data Index: 6689242 (Open Web Text)

Max Activating Token Index: 464

Text #9

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.9543. Min Act: -0.1700

Data Index: 8119798 (Open Web Text)

Max Activating Token Index: 686

Text #10

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.9695. Min Act: -0.1700

Data Index: 7301008 (Open Web Text)

Max Activating Token Index: 787

Text #11

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.9538. Min Act: -0.1700

Data Index: 442019 (Open Web Text)

Max Activating Token Index: 695

Text #12

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.9588. Min Act: -0.1700

Data Index: 4387900 (Open Web Text)

Max Activating Token Index: 118

Text #13

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.9175. Min Act: -0.1700

Data Index: 6199707 (Open Web Text)

Max Activating Token Index: 990

Text #14

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.9033. Min Act: -0.1700

Data Index: 3054474 (Open Web Text)

Max Activating Token Index: 101

Text #15

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.9184. Min Act: -0.1700

Data Index: 3947395 (Open Web Text)

Max Activating Token Index: 78

Text #16

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.9024. Min Act: -0.1700

Data Index: 5640085 (Open Web Text)

Max Activating Token Index: 337

Text #17

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.9070. Min Act: -0.1700

Data Index: 3081087 (Open Web Text)

Max Activating Token Index: 991

Text #18

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.9056. Min Act: -0.1700

Data Index: 4107370 (Open Web Text)

Max Activating Token Index: 446

Text #19

Max Range: 4.1530. Min Range: -4.1530

Max Act: 3.8773. Min Act: -0.1700

Data Index: 2536138 (Open Web Text)

Max Activating Token Index: 168