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

Dataset: Open Web Text

Neuron 2131 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: 3.6303. Min Range: -3.6303

Max Act: 3.6303. Min Act: -0.1700

Data Index: 1834214 (Open Web Text)

Max Activating Token Index: 718

Text #1

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.5047. Min Act: -0.1700

Data Index: 6964348 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.4888. Min Act: -0.1700

Data Index: 2122652 (Open Web Text)

Max Activating Token Index: 469

Text #3

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.4826. Min Act: -0.1700

Data Index: 823596 (Open Web Text)

Max Activating Token Index: 146

Text #4

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.4843. Min Act: -0.1700

Data Index: 495352 (Open Web Text)

Max Activating Token Index: 370

Text #5

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.4550. Min Act: -0.1700

Data Index: 2421807 (Open Web Text)

Max Activating Token Index: 550

Text #6

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.4447. Min Act: -0.1700

Data Index: 2395374 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.4311. Min Act: -0.1700

Data Index: 5729804 (Open Web Text)

Max Activating Token Index: 125

Text #8

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.4441. Min Act: -0.1700

Data Index: 8827278 (Open Web Text)

Max Activating Token Index: 71

Text #9

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.4161. Min Act: -0.1700

Data Index: 4050769 (Open Web Text)

Max Activating Token Index: 48

Text #10

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.4064. Min Act: -0.1700

Data Index: 4967694 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.4143. Min Act: -0.1700

Data Index: 1019573 (Open Web Text)

Max Activating Token Index: 106

Text #12

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.4047. Min Act: -0.1700

Data Index: 6647639 (Open Web Text)

Max Activating Token Index: 643

Text #13

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.3853. Min Act: -0.1700

Data Index: 5656394 (Open Web Text)

Max Activating Token Index: 735

Text #14

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.3741. Min Act: -0.1700

Data Index: 1421819 (Open Web Text)

Max Activating Token Index: 267

Text #15

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.3556. Min Act: -0.1700

Data Index: 2761467 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.3603. Min Act: -0.1700

Data Index: 4958579 (Open Web Text)

Max Activating Token Index: 752

Text #17

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.3293. Min Act: -0.1700

Data Index: 3277863 (Open Web Text)

Max Activating Token Index: 792

Text #18

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.3830. Min Act: -0.1700

Data Index: 4605471 (Open Web Text)

Max Activating Token Index: 312

Text #19

Max Range: 3.6303. Min Range: -3.6303

Max Act: 3.3513. Min Act: -0.1700

Data Index: 4214884 (Open Web Text)

Max Activating Token Index: 25