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

Dataset: Open Web Text

Neuron 2410 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: 4.7310. Min Range: -4.7310

Max Act: 4.7310. Min Act: -0.1700

Data Index: 5864779 (Open Web Text)

Max Activating Token Index: 484

Text #1

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.6526. Min Act: -0.1700

Data Index: 5606910 (Open Web Text)

Max Activating Token Index: 962

Text #2

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.5906. Min Act: -0.1700

Data Index: 8142922 (Open Web Text)

Max Activating Token Index: 713

Text #3

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.5821. Min Act: -0.1700

Data Index: 7371991 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.5850. Min Act: -0.1700

Data Index: 1298178 (Open Web Text)

Max Activating Token Index: 120

Text #5

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.5949. Min Act: -0.1700

Data Index: 8147666 (Open Web Text)

Max Activating Token Index: 75

Text #6

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.5044. Min Act: -0.1700

Data Index: 2710676 (Open Web Text)

Max Activating Token Index: 128

Text #7

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.5180. Min Act: -0.1700

Data Index: 4909017 (Open Web Text)

Max Activating Token Index: 191

Text #8

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.4978. Min Act: -0.1700

Data Index: 8091122 (Open Web Text)

Max Activating Token Index: 681

Text #9

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.5263. Min Act: -0.1700

Data Index: 4721613 (Open Web Text)

Max Activating Token Index: 475

Text #10

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.4880. Min Act: -0.1700

Data Index: 6715074 (Open Web Text)

Max Activating Token Index: 311

Text #11

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.4809. Min Act: -0.1700

Data Index: 5161073 (Open Web Text)

Max Activating Token Index: 734

Text #12

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.4480. Min Act: -0.1700

Data Index: 843662 (Open Web Text)

Max Activating Token Index: 678

Text #13

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.4679. Min Act: -0.1700

Data Index: 8448118 (Open Web Text)

Max Activating Token Index: 652

Text #14

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.4548. Min Act: -0.1700

Data Index: 3866284 (Open Web Text)

Max Activating Token Index: 126

Text #15

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.4661. Min Act: -0.1700

Data Index: 7601543 (Open Web Text)

Max Activating Token Index: 160

Text #16

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.4315. Min Act: -0.1700

Data Index: 1441041 (Open Web Text)

Max Activating Token Index: 419

Text #17

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.4437. Min Act: -0.1700

Data Index: 3213119 (Open Web Text)

Max Activating Token Index: 746

Text #18

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.4339. Min Act: -0.1700

Data Index: 6961906 (Open Web Text)

Max Activating Token Index: 342

Text #19

Max Range: 4.7310. Min Range: -4.7310

Max Act: 4.4709. Min Act: -0.1700

Data Index: 6919519 (Open Web Text)

Max Activating Token Index: 526