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

Dataset: Open Web Text

Neuron 1160 in Layer 2

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: 4.9265. Min Range: -4.9265

Max Act: 4.8954. Min Act: -0.1700

Data Index: 2603963 (Open Web Text)

Max Activating Token Index: 146

Text #1

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.9265. Min Act: -0.1700

Data Index: 1324886 (Open Web Text)

Max Activating Token Index: 616

Text #2

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.8065. Min Act: -0.1700

Data Index: 2603964 (Open Web Text)

Max Activating Token Index: 240

Text #3

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.8282. Min Act: -0.1700

Data Index: 2951139 (Open Web Text)

Max Activating Token Index: 787

Text #4

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.6955. Min Act: -0.1700

Data Index: 3292515 (Open Web Text)

Max Activating Token Index: 643

Text #5

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.6535. Min Act: -0.1700

Data Index: 8683214 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.6270. Min Act: -0.1700

Data Index: 7371109 (Open Web Text)

Max Activating Token Index: 91

Text #7

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.6468. Min Act: -0.1700

Data Index: 3200781 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.6406. Min Act: -0.1700

Data Index: 5445578 (Open Web Text)

Max Activating Token Index: 591

Text #9

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.6266. Min Act: -0.1700

Data Index: 1247375 (Open Web Text)

Max Activating Token Index: 893

Text #10

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.6110. Min Act: -0.1700

Data Index: 2708557 (Open Web Text)

Max Activating Token Index: 74

Text #11

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.6061. Min Act: -0.1700

Data Index: 7629298 (Open Web Text)

Max Activating Token Index: 53

Text #12

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.5925. Min Act: -0.1700

Data Index: 3575909 (Open Web Text)

Max Activating Token Index: 381

Text #13

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.5885. Min Act: -0.1700

Data Index: 4681498 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.5529. Min Act: -0.1700

Data Index: 1533965 (Open Web Text)

Max Activating Token Index: 249

Text #15

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.5636. Min Act: -0.1700

Data Index: 3071498 (Open Web Text)

Max Activating Token Index: 407

Text #16

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.5731. Min Act: -0.1700

Data Index: 1709567 (Open Web Text)

Max Activating Token Index: 679

Text #17

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.5858. Min Act: -0.1700

Data Index: 1763704 (Open Web Text)

Max Activating Token Index: 122

Text #18

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.5383. Min Act: -0.1700

Data Index: 1533966 (Open Web Text)

Max Activating Token Index: 61

Text #19

Max Range: 4.9265. Min Range: -4.9265

Max Act: 4.4981. Min Act: -0.1700

Data Index: 4987418 (Open Web Text)

Max Activating Token Index: 468