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

Dataset: Open Web Text

Neuron 951 in Layer 2

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: 3.4374. Min Range: -3.4374

Max Act: 3.4374. Min Act: -0.1700

Data Index: 4140530 (Open Web Text)

Max Activating Token Index: 165

Text #1

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.4288. Min Act: -0.1700

Data Index: 4437958 (Open Web Text)

Max Activating Token Index: 686

Text #2

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.4008. Min Act: -0.1700

Data Index: 1143269 (Open Web Text)

Max Activating Token Index: 275

Text #3

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.4077. Min Act: -0.1700

Data Index: 30406 (Open Web Text)

Max Activating Token Index: 608

Text #4

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.4159. Min Act: -0.1700

Data Index: 2541904 (Open Web Text)

Max Activating Token Index: 221

Text #5

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.3638. Min Act: -0.1700

Data Index: 4400564 (Open Web Text)

Max Activating Token Index: 101

Text #6

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.3273. Min Act: -0.1700

Data Index: 6314509 (Open Web Text)

Max Activating Token Index: 208

Text #7

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.3448. Min Act: -0.1700

Data Index: 2689050 (Open Web Text)

Max Activating Token Index: 452

Text #8

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.3167. Min Act: -0.1700

Data Index: 7327123 (Open Web Text)

Max Activating Token Index: 393

Text #9

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.3286. Min Act: -0.1700

Data Index: 8556365 (Open Web Text)

Max Activating Token Index: 786

Text #10

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.3164. Min Act: -0.1700

Data Index: 3496992 (Open Web Text)

Max Activating Token Index: 115

Text #11

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.2902. Min Act: -0.1700

Data Index: 3045837 (Open Web Text)

Max Activating Token Index: 63

Text #12

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.3137. Min Act: -0.1700

Data Index: 841708 (Open Web Text)

Max Activating Token Index: 460

Text #13

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.2871. Min Act: -0.1700

Data Index: 1492366 (Open Web Text)

Max Activating Token Index: 783

Text #14

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.2800. Min Act: -0.1700

Data Index: 3331499 (Open Web Text)

Max Activating Token Index: 340

Text #15

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.2937. Min Act: -0.1700

Data Index: 6950586 (Open Web Text)

Max Activating Token Index: 279

Text #16

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.2854. Min Act: -0.1700

Data Index: 8366500 (Open Web Text)

Max Activating Token Index: 83

Text #17

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.2733. Min Act: -0.1700

Data Index: 1524023 (Open Web Text)

Max Activating Token Index: 437

Text #18

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.2736. Min Act: -0.1700

Data Index: 3359552 (Open Web Text)

Max Activating Token Index: 139

Text #19

Max Range: 3.4374. Min Range: -3.4374

Max Act: 3.2785. Min Act: -0.1700

Data Index: 5105234 (Open Web Text)

Max Activating Token Index: 803