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

Dataset: Open Web Text

Neuron 2377 in Layer 1

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: 1.7207. Min Range: -1.7207

Max Act: 1.7207. Min Act: -0.1696

Data Index: 2767251 (Open Web Text)

Max Activating Token Index: 336

Text #1

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.7066. Min Act: -0.1699

Data Index: 6033497 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6994. Min Act: -0.1700

Data Index: 3215521 (Open Web Text)

Max Activating Token Index: 137

Text #3

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.7011. Min Act: -0.1699

Data Index: 1000543 (Open Web Text)

Max Activating Token Index: 300

Text #4

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.7118. Min Act: -0.1700

Data Index: 3345587 (Open Web Text)

Max Activating Token Index: 131

Text #5

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.7080. Min Act: -0.1700

Data Index: 2408927 (Open Web Text)

Max Activating Token Index: 288

Text #6

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6935. Min Act: -0.1700

Data Index: 5312110 (Open Web Text)

Max Activating Token Index: 205

Text #7

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6886. Min Act: -0.1700

Data Index: 1096849 (Open Web Text)

Max Activating Token Index: 693

Text #8

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6850. Min Act: -0.1700

Data Index: 6159085 (Open Web Text)

Max Activating Token Index: 228

Text #9

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6843. Min Act: -0.1700

Data Index: 7088996 (Open Web Text)

Max Activating Token Index: 608

Text #10

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6767. Min Act: -0.1700

Data Index: 3628260 (Open Web Text)

Max Activating Token Index: 810

Text #11

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6725. Min Act: -0.1700

Data Index: 2719613 (Open Web Text)

Max Activating Token Index: 216

Text #12

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6577. Min Act: -0.1700

Data Index: 8613972 (Open Web Text)

Max Activating Token Index: 922

Text #13

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6676. Min Act: -0.1700

Data Index: 5686492 (Open Web Text)

Max Activating Token Index: 553

Text #14

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6597. Min Act: -0.1700

Data Index: 4288929 (Open Web Text)

Max Activating Token Index: 299

Text #15

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6674. Min Act: -0.1700

Data Index: 4980433 (Open Web Text)

Max Activating Token Index: 767

Text #16

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6645. Min Act: -0.1700

Data Index: 769517 (Open Web Text)

Max Activating Token Index: 57

Text #17

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6674. Min Act: -0.1700

Data Index: 1791229 (Open Web Text)

Max Activating Token Index: 167

Text #18

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6614. Min Act: -0.1700

Data Index: 6023825 (Open Web Text)

Max Activating Token Index: 53

Text #19

Max Range: 1.7207. Min Range: -1.7207

Max Act: 1.6616. Min Act: -0.1700

Data Index: 1504582 (Open Web Text)

Max Activating Token Index: 247