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

Dataset: Open Web Text

Neuron 1908 in Layer 5

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: 5.9450. Min Range: -5.9450

Max Act: 5.9450. Min Act: -0.1700

Data Index: 4927759 (Open Web Text)

Max Activating Token Index: 518

Text #1

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.6249. Min Act: -0.1700

Data Index: 6760272 (Open Web Text)

Max Activating Token Index: 338

Text #2

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.6057. Min Act: -0.1700

Data Index: 8030288 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.4846. Min Act: -0.1700

Data Index: 6904043 (Open Web Text)

Max Activating Token Index: 572

Text #4

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.3986. Min Act: -0.1700

Data Index: 3146149 (Open Web Text)

Max Activating Token Index: 268

Text #5

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.4410. Min Act: -0.1700

Data Index: 6260284 (Open Web Text)

Max Activating Token Index: 820

Text #6

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.2841. Min Act: -0.1700

Data Index: 1663939 (Open Web Text)

Max Activating Token Index: 612

Text #7

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.3706. Min Act: -0.1700

Data Index: 1521568 (Open Web Text)

Max Activating Token Index: 228

Text #8

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.2949. Min Act: -0.1700

Data Index: 3732851 (Open Web Text)

Max Activating Token Index: 995

Text #9

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.2925. Min Act: -0.1700

Data Index: 4435331 (Open Web Text)

Max Activating Token Index: 378

Text #10

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.2984. Min Act: -0.1700

Data Index: 2131802 (Open Web Text)

Max Activating Token Index: 716

Text #11

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.3100. Min Act: -0.1700

Data Index: 1019687 (Open Web Text)

Max Activating Token Index: 413

Text #12

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.2425. Min Act: -0.1700

Data Index: 4957807 (Open Web Text)

Max Activating Token Index: 129

Text #13

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.2207. Min Act: -0.1700

Data Index: 8828322 (Open Web Text)

Max Activating Token Index: 736

Text #14

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.1821. Min Act: -0.1700

Data Index: 6240798 (Open Web Text)

Max Activating Token Index: 661

Text #15

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.2043. Min Act: -0.1700

Data Index: 4937172 (Open Web Text)

Max Activating Token Index: 958

Text #16

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.1931. Min Act: -0.1700

Data Index: 2298147 (Open Web Text)

Max Activating Token Index: 225

Text #17

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.2508. Min Act: -0.1700

Data Index: 4374186 (Open Web Text)

Max Activating Token Index: 746

Text #18

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.1862. Min Act: -0.1700

Data Index: 2386448 (Open Web Text)

Max Activating Token Index: 764

Text #19

Max Range: 5.9450. Min Range: -5.9450

Max Act: 5.2216. Min Act: -0.1700

Data Index: 6414452 (Open Web Text)

Max Activating Token Index: 756