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

Dataset: Open Web Text

Neuron 1952 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: 3.8127. Min Range: -3.8127

Max Act: 3.8127. Min Act: -0.1700

Data Index: 1745236 (Open Web Text)

Max Activating Token Index: 501

Text #1

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.7653. Min Act: -0.1700

Data Index: 4502578 (Open Web Text)

Max Activating Token Index: 184

Text #2

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.7008. Min Act: -0.1700

Data Index: 6385965 (Open Web Text)

Max Activating Token Index: 67

Text #3

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6871. Min Act: -0.1700

Data Index: 8412345 (Open Web Text)

Max Activating Token Index: 823

Text #4

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6363. Min Act: -0.1700

Data Index: 1091200 (Open Web Text)

Max Activating Token Index: 992

Text #5

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6516. Min Act: -0.1700

Data Index: 3375409 (Open Web Text)

Max Activating Token Index: 960

Text #6

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6715. Min Act: -0.1700

Data Index: 1700462 (Open Web Text)

Max Activating Token Index: 784

Text #7

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6597. Min Act: -0.1700

Data Index: 1713096 (Open Web Text)

Max Activating Token Index: 131

Text #8

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6295. Min Act: -0.1700

Data Index: 7449022 (Open Web Text)

Max Activating Token Index: 669

Text #9

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6360. Min Act: -0.1700

Data Index: 3015123 (Open Web Text)

Max Activating Token Index: 601

Text #10

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6086. Min Act: -0.1700

Data Index: 3531676 (Open Web Text)

Max Activating Token Index: 44

Text #11

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.5907. Min Act: -0.1700

Data Index: 5218895 (Open Web Text)

Max Activating Token Index: 114

Text #12

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6026. Min Act: -0.1700

Data Index: 1547806 (Open Web Text)

Max Activating Token Index: 360

Text #13

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6119. Min Act: -0.1700

Data Index: 8357498 (Open Web Text)

Max Activating Token Index: 1011

Text #14

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6202. Min Act: -0.1700

Data Index: 915023 (Open Web Text)

Max Activating Token Index: 52

Text #15

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.6377. Min Act: -0.1700

Data Index: 4868259 (Open Web Text)

Max Activating Token Index: 822

Text #16

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.5744. Min Act: -0.1700

Data Index: 7430001 (Open Web Text)

Max Activating Token Index: 871

Text #17

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.5788. Min Act: -0.1700

Data Index: 6973389 (Open Web Text)

Max Activating Token Index: 973

Text #18

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.5314. Min Act: -0.1700

Data Index: 4393485 (Open Web Text)

Max Activating Token Index: 401

Text #19

Max Range: 3.8127. Min Range: -3.8127

Max Act: 3.5530. Min Act: -0.1700

Data Index: 5052902 (Open Web Text)

Max Activating Token Index: 674