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

Dataset: Open Web Text

Neuron 46 in Layer 5

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: 4.9950. Min Range: -4.9950

Max Act: 4.9950. Min Act: -0.1700

Data Index: 4830236 (Open Web Text)

Max Activating Token Index: 327

Text #1

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.8062. Min Act: -0.1700

Data Index: 8454701 (Open Web Text)

Max Activating Token Index: 472

Text #2

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.6414. Min Act: -0.1700

Data Index: 2934044 (Open Web Text)

Max Activating Token Index: 120

Text #3

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.6485. Min Act: -0.1700

Data Index: 2657227 (Open Web Text)

Max Activating Token Index: 845

Text #4

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.6034. Min Act: -0.1700

Data Index: 2894006 (Open Web Text)

Max Activating Token Index: 964

Text #5

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.5670. Min Act: -0.1700

Data Index: 7507639 (Open Web Text)

Max Activating Token Index: 560

Text #6

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.5341. Min Act: -0.1700

Data Index: 8638450 (Open Web Text)

Max Activating Token Index: 763

Text #7

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.5203. Min Act: -0.1700

Data Index: 3618895 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.5414. Min Act: -0.1700

Data Index: 717844 (Open Web Text)

Max Activating Token Index: 479

Text #9

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.4951. Min Act: -0.1700

Data Index: 716009 (Open Web Text)

Max Activating Token Index: 295

Text #10

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.4801. Min Act: -0.1700

Data Index: 4806892 (Open Web Text)

Max Activating Token Index: 27

Text #11

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.5210. Min Act: -0.1700

Data Index: 1713461 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.5190. Min Act: -0.1700

Data Index: 2829537 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.5208. Min Act: -0.1700

Data Index: 8292129 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.4881. Min Act: -0.1700

Data Index: 6578222 (Open Web Text)

Max Activating Token Index: 872

Text #15

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.5336. Min Act: -0.1700

Data Index: 6288021 (Open Web Text)

Max Activating Token Index: 582

Text #16

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.4682. Min Act: -0.1700

Data Index: 7755959 (Open Web Text)

Max Activating Token Index: 567

Text #17

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.4864. Min Act: -0.1700

Data Index: 7843328 (Open Web Text)

Max Activating Token Index: 128

Text #18

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.4887. Min Act: -0.1700

Data Index: 1003583 (Open Web Text)

Max Activating Token Index: 985

Text #19

Max Range: 4.9950. Min Range: -4.9950

Max Act: 4.5107. Min Act: -0.1700

Data Index: 4344683 (Open Web Text)

Max Activating Token Index: 590