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

Dataset: Open Web Text

Neuron 895 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: 6.7672. Min Range: -6.7672

Max Act: 6.7672. Min Act: -0.1700

Data Index: 1836114 (Open Web Text)

Max Activating Token Index: 436

Text #1

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.6804. Min Act: -0.1700

Data Index: 3469788 (Open Web Text)

Max Activating Token Index: 897

Text #2

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.6369. Min Act: -0.1700

Data Index: 4710252 (Open Web Text)

Max Activating Token Index: 129

Text #3

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.5623. Min Act: -0.1700

Data Index: 2216720 (Open Web Text)

Max Activating Token Index: 398

Text #4

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.4861. Min Act: -0.1700

Data Index: 1169377 (Open Web Text)

Max Activating Token Index: 95

Text #5

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.5797. Min Act: -0.1700

Data Index: 1836111 (Open Web Text)

Max Activating Token Index: 753

Text #6

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.5278. Min Act: -0.1700

Data Index: 4194484 (Open Web Text)

Max Activating Token Index: 317

Text #7

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.5146. Min Act: -0.1700

Data Index: 8519782 (Open Web Text)

Max Activating Token Index: 832

Text #8

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.5605. Min Act: -0.1700

Data Index: 8626091 (Open Web Text)

Max Activating Token Index: 478

Text #9

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.5330. Min Act: -0.1700

Data Index: 5811474 (Open Web Text)

Max Activating Token Index: 310

Text #10

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.5022. Min Act: -0.1700

Data Index: 3964753 (Open Web Text)

Max Activating Token Index: 336

Text #11

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.4767. Min Act: -0.1700

Data Index: 5272632 (Open Web Text)

Max Activating Token Index: 665

Text #12

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.4705. Min Act: -0.1700

Data Index: 2202265 (Open Web Text)

Max Activating Token Index: 52

Text #13

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.4832. Min Act: -0.1700

Data Index: 1238585 (Open Web Text)

Max Activating Token Index: 236

Text #14

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.5120. Min Act: -0.1700

Data Index: 2136067 (Open Web Text)

Max Activating Token Index: 774

Text #15

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.5073. Min Act: -0.1700

Data Index: 7584900 (Open Web Text)

Max Activating Token Index: 816

Text #16

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.4338. Min Act: -0.1700

Data Index: 7975305 (Open Web Text)

Max Activating Token Index: 156

Text #17

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.4548. Min Act: -0.1700

Data Index: 3947344 (Open Web Text)

Max Activating Token Index: 558

Text #18

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.4156. Min Act: -0.1700

Data Index: 7661919 (Open Web Text)

Max Activating Token Index: 580

Text #19

Max Range: 6.7672. Min Range: -6.7672

Max Act: 6.4226. Min Act: -0.1700

Data Index: 4566389 (Open Web Text)

Max Activating Token Index: 443