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

Dataset: Open Web Text

Neuron 641 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: 3.0225. Min Range: -3.0225

Max Act: 3.0225. Min Act: -0.1700

Data Index: 3129616 (Open Web Text)

Max Activating Token Index: 155

Text #1

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9655. Min Act: -0.1700

Data Index: 3636851 (Open Web Text)

Max Activating Token Index: 990

Text #2

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9152. Min Act: -0.1700

Data Index: 7935361 (Open Web Text)

Max Activating Token Index: 808

Text #3

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.9183. Min Act: -0.1700

Data Index: 1012734 (Open Web Text)

Max Activating Token Index: 314

Text #4

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8995. Min Act: -0.1700

Data Index: 3238860 (Open Web Text)

Max Activating Token Index: 599

Text #5

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8692. Min Act: -0.1700

Data Index: 7054825 (Open Web Text)

Max Activating Token Index: 658

Text #6

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8643. Min Act: -0.1700

Data Index: 6822565 (Open Web Text)

Max Activating Token Index: 556

Text #7

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8342. Min Act: -0.1700

Data Index: 1117236 (Open Web Text)

Max Activating Token Index: 498

Text #8

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8565. Min Act: -0.1700

Data Index: 3550278 (Open Web Text)

Max Activating Token Index: 335

Text #9

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8402. Min Act: -0.1700

Data Index: 3090166 (Open Web Text)

Max Activating Token Index: 778

Text #10

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8182. Min Act: -0.1700

Data Index: 6489233 (Open Web Text)

Max Activating Token Index: 292

Text #11

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8288. Min Act: -0.1700

Data Index: 2969759 (Open Web Text)

Max Activating Token Index: 805

Text #12

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8122. Min Act: -0.1700

Data Index: 2422749 (Open Web Text)

Max Activating Token Index: 862

Text #13

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8243. Min Act: -0.1700

Data Index: 6763996 (Open Web Text)

Max Activating Token Index: 946

Text #14

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.8004. Min Act: -0.1700

Data Index: 4591079 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.7988. Min Act: -0.1700

Data Index: 68556 (Open Web Text)

Max Activating Token Index: 370

Text #16

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.7763. Min Act: -0.1700

Data Index: 3833041 (Open Web Text)

Max Activating Token Index: 751

Text #17

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.7961. Min Act: -0.1700

Data Index: 2493709 (Open Web Text)

Max Activating Token Index: 741

Text #18

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.7778. Min Act: -0.1700

Data Index: 906897 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 3.0225. Min Range: -3.0225

Max Act: 2.7612. Min Act: -0.1700

Data Index: 6659179 (Open Web Text)

Max Activating Token Index: 839