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

Dataset: Open Web Text

Neuron 382 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: 3.2994. Min Range: -3.2994

Max Act: 3.2994. Min Act: -0.1700

Data Index: 3324595 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.2383. Min Act: -0.1700

Data Index: 1956635 (Open Web Text)

Max Activating Token Index: 921

Text #2

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.1672. Min Act: -0.1700

Data Index: 1266762 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.1056. Min Act: -0.1700

Data Index: 3427257 (Open Web Text)

Max Activating Token Index: 270

Text #4

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0913. Min Act: -0.1700

Data Index: 632652 (Open Web Text)

Max Activating Token Index: 899

Text #5

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.1106. Min Act: -0.1700

Data Index: 7883754 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.1053. Min Act: -0.1700

Data Index: 3622435 (Open Web Text)

Max Activating Token Index: 926

Text #7

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.1093. Min Act: -0.1700

Data Index: 6445477 (Open Web Text)

Max Activating Token Index: 154

Text #8

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0953. Min Act: -0.1700

Data Index: 2829960 (Open Web Text)

Max Activating Token Index: 632

Text #9

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0714. Min Act: -0.1700

Data Index: 601157 (Open Web Text)

Max Activating Token Index: 846

Text #10

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0703. Min Act: -0.1700

Data Index: 8378317 (Open Web Text)

Max Activating Token Index: 619

Text #11

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0721. Min Act: -0.1700

Data Index: 5275224 (Open Web Text)

Max Activating Token Index: 896

Text #12

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0769. Min Act: -0.1700

Data Index: 4639885 (Open Web Text)

Max Activating Token Index: 127

Text #13

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0667. Min Act: -0.1700

Data Index: 3431327 (Open Web Text)

Max Activating Token Index: 83

Text #14

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0305. Min Act: -0.1700

Data Index: 2474020 (Open Web Text)

Max Activating Token Index: 640

Text #15

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0569. Min Act: -0.1700

Data Index: 6361001 (Open Web Text)

Max Activating Token Index: 265

Text #16

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0504. Min Act: -0.1700

Data Index: 835319 (Open Web Text)

Max Activating Token Index: 579

Text #17

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0501. Min Act: -0.1700

Data Index: 3363562 (Open Web Text)

Max Activating Token Index: 320

Text #18

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0572. Min Act: -0.1700

Data Index: 3736929 (Open Web Text)

Max Activating Token Index: 170

Text #19

Max Range: 3.2994. Min Range: -3.2994

Max Act: 3.0617. Min Act: -0.1700

Data Index: 7098054 (Open Web Text)

Max Activating Token Index: 948