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

Dataset: Open Web Text

Neuron 2656 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: 3.1807. Min Range: -3.1807

Max Act: 3.1807. Min Act: -0.1700

Data Index: 707210 (Open Web Text)

Max Activating Token Index: 616

Text #1

Max Range: 3.1807. Min Range: -3.1807

Max Act: 3.0225. Min Act: -0.1700

Data Index: 4652145 (Open Web Text)

Max Activating Token Index: 355

Text #2

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.9585. Min Act: -0.1700

Data Index: 1711071 (Open Web Text)

Max Activating Token Index: 725

Text #3

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8993. Min Act: -0.1700

Data Index: 3699178 (Open Web Text)

Max Activating Token Index: 854

Text #4

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8745. Min Act: -0.1700

Data Index: 7350693 (Open Web Text)

Max Activating Token Index: 190

Text #5

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8763. Min Act: -0.1700

Data Index: 1764753 (Open Web Text)

Max Activating Token Index: 526

Text #6

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8703. Min Act: -0.1700

Data Index: 6688014 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8514. Min Act: -0.1700

Data Index: 4233287 (Open Web Text)

Max Activating Token Index: 322

Text #8

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8505. Min Act: -0.1700

Data Index: 8135544 (Open Web Text)

Max Activating Token Index: 361

Text #9

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8450. Min Act: -0.1700

Data Index: 5803520 (Open Web Text)

Max Activating Token Index: 321

Text #10

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8437. Min Act: -0.1700

Data Index: 1591009 (Open Web Text)

Max Activating Token Index: 820

Text #11

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8165. Min Act: -0.1700

Data Index: 5983086 (Open Web Text)

Max Activating Token Index: 876

Text #12

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8355. Min Act: -0.1700

Data Index: 8304372 (Open Web Text)

Max Activating Token Index: 729

Text #13

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8124. Min Act: -0.1700

Data Index: 6381932 (Open Web Text)

Max Activating Token Index: 784

Text #14

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.7985. Min Act: -0.1700

Data Index: 205977 (Open Web Text)

Max Activating Token Index: 129

Text #15

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8154. Min Act: -0.1700

Data Index: 822464 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8088. Min Act: -0.1700

Data Index: 7800688 (Open Web Text)

Max Activating Token Index: 343

Text #17

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.8024. Min Act: -0.1700

Data Index: 5993759 (Open Web Text)

Max Activating Token Index: 177

Text #18

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.7930. Min Act: -0.1700

Data Index: 6950842 (Open Web Text)

Max Activating Token Index: 804

Text #19

Max Range: 3.1807. Min Range: -3.1807

Max Act: 2.7939. Min Act: -0.1700

Data Index: 7533500 (Open Web Text)

Max Activating Token Index: 669