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

Dataset: Open Web Text

Neuron 1018 in Layer 3

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: 2.5487. Min Range: -2.5487

Max Act: 2.5487. Min Act: -0.1700

Data Index: 6722726 (Open Web Text)

Max Activating Token Index: 413

Text #1

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.4704. Min Act: -0.1700

Data Index: 7560052 (Open Web Text)

Max Activating Token Index: 882

Text #2

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.4778. Min Act: -0.1700

Data Index: 3394763 (Open Web Text)

Max Activating Token Index: 332

Text #3

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.4795. Min Act: -0.1700

Data Index: 5572352 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.4795. Min Act: -0.1700

Data Index: 7935772 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.4472. Min Act: -0.1700

Data Index: 5724889 (Open Web Text)

Max Activating Token Index: 764

Text #6

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.4578. Min Act: -0.1700

Data Index: 7345633 (Open Web Text)

Max Activating Token Index: 332

Text #7

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.4411. Min Act: -0.1700

Data Index: 7623165 (Open Web Text)

Max Activating Token Index: 387

Text #8

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.4175. Min Act: -0.1700

Data Index: 7686641 (Open Web Text)

Max Activating Token Index: 117

Text #9

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.4091. Min Act: -0.1700

Data Index: 2772346 (Open Web Text)

Max Activating Token Index: 524

Text #10

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.3658. Min Act: -0.1700

Data Index: 6215548 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.4009. Min Act: -0.1700

Data Index: 8402236 (Open Web Text)

Max Activating Token Index: 610

Text #12

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.3970. Min Act: -0.1700

Data Index: 2661933 (Open Web Text)

Max Activating Token Index: 640

Text #13

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.4070. Min Act: -0.1700

Data Index: 4022582 (Open Web Text)

Max Activating Token Index: 777

Text #14

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.3584. Min Act: -0.1700

Data Index: 6467174 (Open Web Text)

Max Activating Token Index: 50

Text #15

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.3202. Min Act: -0.1700

Data Index: 4641381 (Open Web Text)

Max Activating Token Index: 701

Text #16

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.3326. Min Act: -0.1700

Data Index: 7407162 (Open Web Text)

Max Activating Token Index: 809

Text #17

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.3315. Min Act: -0.1700

Data Index: 2373910 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.3285. Min Act: -0.1700

Data Index: 6655852 (Open Web Text)

Max Activating Token Index: 812

Text #19

Max Range: 2.5487. Min Range: -2.5487

Max Act: 2.3122. Min Act: -0.1700

Data Index: 4956248 (Open Web Text)

Max Activating Token Index: 376