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

Dataset: Open Web Text

Neuron 3069 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: 4.0472. Min Range: -4.0472

Max Act: 4.0472. Min Act: -0.1700

Data Index: 3361000 (Open Web Text)

Max Activating Token Index: 749

Text #1

Max Range: 4.0472. Min Range: -4.0472

Max Act: 4.0416. Min Act: -0.1700

Data Index: 8083559 (Open Web Text)

Max Activating Token Index: 407

Text #2

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.9665. Min Act: -0.1700

Data Index: 1537464 (Open Web Text)

Max Activating Token Index: 921

Text #3

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.9969. Min Act: -0.1700

Data Index: 8062927 (Open Web Text)

Max Activating Token Index: 879

Text #4

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.9143. Min Act: -0.1700

Data Index: 8741960 (Open Web Text)

Max Activating Token Index: 129

Text #5

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.8553. Min Act: -0.1700

Data Index: 1555042 (Open Web Text)

Max Activating Token Index: 601

Text #6

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7791. Min Act: -0.1700

Data Index: 7142353 (Open Web Text)

Max Activating Token Index: 535

Text #7

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7943. Min Act: -0.1700

Data Index: 6948968 (Open Web Text)

Max Activating Token Index: 970

Text #8

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7325. Min Act: -0.1700

Data Index: 6691794 (Open Web Text)

Max Activating Token Index: 565

Text #9

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7184. Min Act: -0.1700

Data Index: 2787886 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7249. Min Act: -0.1700

Data Index: 1054796 (Open Web Text)

Max Activating Token Index: 451

Text #11

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7283. Min Act: -0.1700

Data Index: 2488653 (Open Web Text)

Max Activating Token Index: 824

Text #12

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7200. Min Act: -0.1700

Data Index: 4238890 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7256. Min Act: -0.1700

Data Index: 8084858 (Open Web Text)

Max Activating Token Index: 699

Text #14

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7162. Min Act: -0.1700

Data Index: 5700053 (Open Web Text)

Max Activating Token Index: 291

Text #15

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7115. Min Act: -0.1700

Data Index: 925702 (Open Web Text)

Max Activating Token Index: 516

Text #16

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7393. Min Act: -0.1700

Data Index: 3735193 (Open Web Text)

Max Activating Token Index: 554

Text #17

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7280. Min Act: -0.1700

Data Index: 4611719 (Open Web Text)

Max Activating Token Index: 1018

Text #18

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7055. Min Act: -0.1700

Data Index: 8448905 (Open Web Text)

Max Activating Token Index: 771

Text #19

Max Range: 4.0472. Min Range: -4.0472

Max Act: 3.7172. Min Act: -0.1700

Data Index: 8595273 (Open Web Text)

Max Activating Token Index: 241