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

Dataset: Open Web Text

Neuron 1959 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: 3.4203. Min Range: -3.4203

Max Act: 3.4203. Min Act: -0.1700

Data Index: 6887047 (Open Web Text)

Max Activating Token Index: 188

Text #1

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.3832. Min Act: -0.1700

Data Index: 1851575 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.4016. Min Act: -0.1700

Data Index: 104167 (Open Web Text)

Max Activating Token Index: 151

Text #3

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.3430. Min Act: -0.1700

Data Index: 1109389 (Open Web Text)

Max Activating Token Index: 40

Text #4

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.3173. Min Act: -0.1700

Data Index: 3602319 (Open Web Text)

Max Activating Token Index: 932

Text #5

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.3907. Min Act: -0.1700

Data Index: 5809937 (Open Web Text)

Max Activating Token Index: 620

Text #6

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.3479. Min Act: -0.1700

Data Index: 8661965 (Open Web Text)

Max Activating Token Index: 685

Text #7

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.3435. Min Act: -0.1700

Data Index: 4381339 (Open Web Text)

Max Activating Token Index: 444

Text #8

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.3405. Min Act: -0.1700

Data Index: 3347620 (Open Web Text)

Max Activating Token Index: 811

Text #9

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2903. Min Act: -0.1700

Data Index: 7346574 (Open Web Text)

Max Activating Token Index: 740

Text #10

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2327. Min Act: -0.1700

Data Index: 1231262 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2598. Min Act: -0.1700

Data Index: 7027829 (Open Web Text)

Max Activating Token Index: 424

Text #12

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2354. Min Act: -0.1700

Data Index: 5069959 (Open Web Text)

Max Activating Token Index: 179

Text #13

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2165. Min Act: -0.1700

Data Index: 8021851 (Open Web Text)

Max Activating Token Index: 359

Text #14

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2214. Min Act: -0.1700

Data Index: 4864391 (Open Web Text)

Max Activating Token Index: 837

Text #15

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2563. Min Act: -0.1700

Data Index: 3638452 (Open Web Text)

Max Activating Token Index: 364

Text #16

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2180. Min Act: -0.1700

Data Index: 378812 (Open Web Text)

Max Activating Token Index: 639

Text #17

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.1941. Min Act: -0.1700

Data Index: 2552210 (Open Web Text)

Max Activating Token Index: 569

Text #18

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2800. Min Act: -0.1700

Data Index: 1910263 (Open Web Text)

Max Activating Token Index: 602

Text #19

Max Range: 3.4203. Min Range: -3.4203

Max Act: 3.2752. Min Act: -0.1700

Data Index: 3943958 (Open Web Text)

Max Activating Token Index: 43