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

Dataset: Open Web Text

Neuron 1088 in Layer 6

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: 6.4864. Min Range: -6.4864

Max Act: 6.4864. Min Act: -0.1700

Data Index: 7875345 (Open Web Text)

Max Activating Token Index: 692

Text #1

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.4624. Min Act: -0.1700

Data Index: 7543556 (Open Web Text)

Max Activating Token Index: 643

Text #2

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.2921. Min Act: -0.1700

Data Index: 3095674 (Open Web Text)

Max Activating Token Index: 144

Text #3

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.2577. Min Act: -0.1700

Data Index: 3596046 (Open Web Text)

Max Activating Token Index: 908

Text #4

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.2641. Min Act: -0.1700

Data Index: 3590862 (Open Web Text)

Max Activating Token Index: 431

Text #5

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.2260. Min Act: -0.1700

Data Index: 3095775 (Open Web Text)

Max Activating Token Index: 174

Text #6

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1898. Min Act: -0.1700

Data Index: 2812266 (Open Web Text)

Max Activating Token Index: 228

Text #7

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1926. Min Act: -0.1700

Data Index: 793507 (Open Web Text)

Max Activating Token Index: 960

Text #8

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1622. Min Act: -0.1700

Data Index: 7990421 (Open Web Text)

Max Activating Token Index: 759

Text #9

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1578. Min Act: -0.1700

Data Index: 8663672 (Open Web Text)

Max Activating Token Index: 562

Text #10

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1779. Min Act: -0.1700

Data Index: 4695961 (Open Web Text)

Max Activating Token Index: 105

Text #11

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1669. Min Act: -0.1700

Data Index: 2813650 (Open Web Text)

Max Activating Token Index: 868

Text #12

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1918. Min Act: -0.1700

Data Index: 3400228 (Open Web Text)

Max Activating Token Index: 818

Text #13

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1373. Min Act: -0.1700

Data Index: 8380237 (Open Web Text)

Max Activating Token Index: 932

Text #14

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1471. Min Act: -0.1700

Data Index: 3693118 (Open Web Text)

Max Activating Token Index: 35

Text #15

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.0961. Min Act: -0.1700

Data Index: 5939445 (Open Web Text)

Max Activating Token Index: 906

Text #16

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1363. Min Act: -0.1700

Data Index: 6073724 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.1091. Min Act: -0.1700

Data Index: 1823290 (Open Web Text)

Max Activating Token Index: 810

Text #18

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.0993. Min Act: -0.1700

Data Index: 3134027 (Open Web Text)

Max Activating Token Index: 112

Text #19

Max Range: 6.4864. Min Range: -6.4864

Max Act: 6.0429. Min Act: -0.1700

Data Index: 7768149 (Open Web Text)

Max Activating Token Index: 583