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

Dataset: Open Web Text

Neuron 2253 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: 3.0815. Min Range: -3.0815

Max Act: 3.0815. Min Act: -0.1700

Data Index: 6381699 (Open Web Text)

Max Activating Token Index: 742

Text #1

Max Range: 3.0815. Min Range: -3.0815

Max Act: 3.0509. Min Act: -0.1700

Data Index: 837043 (Open Web Text)

Max Activating Token Index: 473

Text #2

Max Range: 3.0815. Min Range: -3.0815

Max Act: 3.0213. Min Act: -0.1700

Data Index: 3423350 (Open Web Text)

Max Activating Token Index: 325

Text #3

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9921. Min Act: -0.1700

Data Index: 6072697 (Open Web Text)

Max Activating Token Index: 391

Text #4

Max Range: 3.0815. Min Range: -3.0815

Max Act: 3.0272. Min Act: -0.1700

Data Index: 4696384 (Open Web Text)

Max Activating Token Index: 522

Text #5

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9861. Min Act: -0.1700

Data Index: 730967 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9816. Min Act: -0.1700

Data Index: 502318 (Open Web Text)

Max Activating Token Index: 700

Text #7

Max Range: 3.0815. Min Range: -3.0815

Max Act: 3.0040. Min Act: -0.1700

Data Index: 1102963 (Open Web Text)

Max Activating Token Index: 1022

Text #8

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9812. Min Act: -0.1700

Data Index: 3332580 (Open Web Text)

Max Activating Token Index: 1011

Text #9

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9655. Min Act: -0.1700

Data Index: 3699949 (Open Web Text)

Max Activating Token Index: 210

Text #10

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9562. Min Act: -0.1700

Data Index: 6502220 (Open Web Text)

Max Activating Token Index: 193

Text #11

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9598. Min Act: -0.1700

Data Index: 64506 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9707. Min Act: -0.1700

Data Index: 3716524 (Open Web Text)

Max Activating Token Index: 452

Text #13

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9415. Min Act: -0.1700

Data Index: 3170974 (Open Web Text)

Max Activating Token Index: 128

Text #14

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9598. Min Act: -0.1700

Data Index: 1359278 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9598. Min Act: -0.1700

Data Index: 5170597 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9532. Min Act: -0.1700

Data Index: 6822284 (Open Web Text)

Max Activating Token Index: 284

Text #17

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9792. Min Act: -0.1700

Data Index: 3984728 (Open Web Text)

Max Activating Token Index: 387

Text #18

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9431. Min Act: -0.1700

Data Index: 6986152 (Open Web Text)

Max Activating Token Index: 693

Text #19

Max Range: 3.0815. Min Range: -3.0815

Max Act: 2.9154. Min Act: -0.1700

Data Index: 3115160 (Open Web Text)

Max Activating Token Index: 442