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

Dataset: Open Web Text

Neuron 2010 in Layer 4

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: 3.5641. Min Range: -3.5641

Max Act: 3.5641. Min Act: -0.1700

Data Index: 4954123 (Open Web Text)

Max Activating Token Index: 169

Text #1

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.5493. Min Act: -0.1700

Data Index: 7085157 (Open Web Text)

Max Activating Token Index: 928

Text #2

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3536. Min Act: -0.1700

Data Index: 3203541 (Open Web Text)

Max Activating Token Index: 880

Text #3

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3852. Min Act: -0.1700

Data Index: 6237233 (Open Web Text)

Max Activating Token Index: 378

Text #4

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.3231. Min Act: -0.1700

Data Index: 1840645 (Open Web Text)

Max Activating Token Index: 811

Text #5

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2330. Min Act: -0.1700

Data Index: 631551 (Open Web Text)

Max Activating Token Index: 834

Text #6

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2280. Min Act: -0.1700

Data Index: 2044473 (Open Web Text)

Max Activating Token Index: 378

Text #7

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.2146. Min Act: -0.1700

Data Index: 640985 (Open Web Text)

Max Activating Token Index: 610

Text #8

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1702. Min Act: -0.1700

Data Index: 70623 (Open Web Text)

Max Activating Token Index: 257

Text #9

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1742. Min Act: -0.1700

Data Index: 5871736 (Open Web Text)

Max Activating Token Index: 523

Text #10

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1881. Min Act: -0.1700

Data Index: 3563561 (Open Web Text)

Max Activating Token Index: 1018

Text #11

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1814. Min Act: -0.1700

Data Index: 7743055 (Open Web Text)

Max Activating Token Index: 518

Text #12

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1144. Min Act: -0.1700

Data Index: 3636287 (Open Web Text)

Max Activating Token Index: 968

Text #13

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1247. Min Act: -0.1700

Data Index: 6832292 (Open Web Text)

Max Activating Token Index: 188

Text #14

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1254. Min Act: -0.1700

Data Index: 3337098 (Open Web Text)

Max Activating Token Index: 177

Text #15

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1069. Min Act: -0.1700

Data Index: 7346811 (Open Web Text)

Max Activating Token Index: 405

Text #16

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1119. Min Act: -0.1700

Data Index: 8011545 (Open Web Text)

Max Activating Token Index: 213

Text #17

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1364. Min Act: -0.1700

Data Index: 3892524 (Open Web Text)

Max Activating Token Index: 924

Text #18

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.1169. Min Act: -0.1700

Data Index: 6581541 (Open Web Text)

Max Activating Token Index: 689

Text #19

Max Range: 3.5641. Min Range: -3.5641

Max Act: 3.0711. Min Act: -0.1700

Data Index: 6651112 (Open Web Text)

Max Activating Token Index: 563