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

Dataset: Open Web Text

Neuron 465 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: 5.4232. Min Range: -5.4232

Max Act: 5.4232. Min Act: -0.1700

Data Index: 1439588 (Open Web Text)

Max Activating Token Index: 113

Text #1

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.4031. Min Act: -0.1700

Data Index: 2426233 (Open Web Text)

Max Activating Token Index: 600

Text #2

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.3458. Min Act: -0.1700

Data Index: 1952295 (Open Web Text)

Max Activating Token Index: 965

Text #3

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.2703. Min Act: -0.1700

Data Index: 5577559 (Open Web Text)

Max Activating Token Index: 553

Text #4

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.2130. Min Act: -0.1700

Data Index: 852828 (Open Web Text)

Max Activating Token Index: 770

Text #5

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.2139. Min Act: -0.1700

Data Index: 7549709 (Open Web Text)

Max Activating Token Index: 253

Text #6

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.2204. Min Act: -0.1700

Data Index: 2214776 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.2043. Min Act: -0.1700

Data Index: 6568435 (Open Web Text)

Max Activating Token Index: 663

Text #8

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.1964. Min Act: -0.1700

Data Index: 4577260 (Open Web Text)

Max Activating Token Index: 192

Text #9

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.1551. Min Act: -0.1700

Data Index: 1983680 (Open Web Text)

Max Activating Token Index: 186

Text #10

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.1597. Min Act: -0.1700

Data Index: 3448769 (Open Web Text)

Max Activating Token Index: 64

Text #11

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.1621. Min Act: -0.1700

Data Index: 6512429 (Open Web Text)

Max Activating Token Index: 336

Text #12

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.1646. Min Act: -0.1700

Data Index: 8231735 (Open Web Text)

Max Activating Token Index: 1005

Text #13

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.0906. Min Act: -0.1700

Data Index: 8100108 (Open Web Text)

Max Activating Token Index: 103

Text #14

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.0980. Min Act: -0.1700

Data Index: 7538543 (Open Web Text)

Max Activating Token Index: 943

Text #15

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.0941. Min Act: -0.1700

Data Index: 7132981 (Open Web Text)

Max Activating Token Index: 439

Text #16

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.1062. Min Act: -0.1700

Data Index: 1429206 (Open Web Text)

Max Activating Token Index: 705

Text #17

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.0739. Min Act: -0.1700

Data Index: 8772959 (Open Web Text)

Max Activating Token Index: 75

Text #18

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.0675. Min Act: -0.1700

Data Index: 3448768 (Open Web Text)

Max Activating Token Index: 810

Text #19

Max Range: 5.4232. Min Range: -5.4232

Max Act: 5.0428. Min Act: -0.1700

Data Index: 4500076 (Open Web Text)

Max Activating Token Index: 275