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

Dataset: Open Web Text

Neuron 2726 in Layer 3

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: 4.2810. Min Range: -4.2810

Max Act: 4.2810. Min Act: -0.1700

Data Index: 8807785 (Open Web Text)

Max Activating Token Index: 66

Text #1

Max Range: 4.2810. Min Range: -4.2810

Max Act: 4.2548. Min Act: -0.1700

Data Index: 7972942 (Open Web Text)

Max Activating Token Index: 512

Text #2

Max Range: 4.2810. Min Range: -4.2810

Max Act: 4.1529. Min Act: -0.1700

Data Index: 4198110 (Open Web Text)

Max Activating Token Index: 867

Text #3

Max Range: 4.2810. Min Range: -4.2810

Max Act: 4.1135. Min Act: -0.1700

Data Index: 3395342 (Open Web Text)

Max Activating Token Index: 403

Text #4

Max Range: 4.2810. Min Range: -4.2810

Max Act: 4.0276. Min Act: -0.1700

Data Index: 1191498 (Open Web Text)

Max Activating Token Index: 108

Text #5

Max Range: 4.2810. Min Range: -4.2810

Max Act: 4.0063. Min Act: -0.1700

Data Index: 5258185 (Open Web Text)

Max Activating Token Index: 555

Text #6

Max Range: 4.2810. Min Range: -4.2810

Max Act: 4.0010. Min Act: -0.1700

Data Index: 8449540 (Open Web Text)

Max Activating Token Index: 716

Text #7

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.9900. Min Act: -0.1700

Data Index: 5226752 (Open Web Text)

Max Activating Token Index: 581

Text #8

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.9788. Min Act: -0.1700

Data Index: 6259864 (Open Web Text)

Max Activating Token Index: 278

Text #9

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.9773. Min Act: -0.1700

Data Index: 897294 (Open Web Text)

Max Activating Token Index: 394

Text #10

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.9111. Min Act: -0.1700

Data Index: 5025243 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.8874. Min Act: -0.1700

Data Index: 2817423 (Open Web Text)

Max Activating Token Index: 428

Text #12

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.8811. Min Act: -0.1700

Data Index: 3298677 (Open Web Text)

Max Activating Token Index: 184

Text #13

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.8860. Min Act: -0.1700

Data Index: 3327585 (Open Web Text)

Max Activating Token Index: 359

Text #14

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.8971. Min Act: -0.1700

Data Index: 8441142 (Open Web Text)

Max Activating Token Index: 645

Text #15

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.8970. Min Act: -0.1700

Data Index: 5990031 (Open Web Text)

Max Activating Token Index: 192

Text #16

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.8792. Min Act: -0.1700

Data Index: 467709 (Open Web Text)

Max Activating Token Index: 385

Text #17

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.8942. Min Act: -0.1700

Data Index: 8020189 (Open Web Text)

Max Activating Token Index: 661

Text #18

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.8560. Min Act: -0.1700

Data Index: 7702079 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 4.2810. Min Range: -4.2810

Max Act: 3.8582. Min Act: -0.1700

Data Index: 2156572 (Open Web Text)

Max Activating Token Index: 685