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

Dataset: Open Web Text

Neuron 1719 in Layer 6

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: 5.0576. Min Range: -5.0576

Max Act: 5.0440. Min Act: -0.1700

Data Index: 7274643 (Open Web Text)

Max Activating Token Index: 353

Text #1

Max Range: 5.0576. Min Range: -5.0576

Max Act: 5.0406. Min Act: -0.1700

Data Index: 5795409 (Open Web Text)

Max Activating Token Index: 979

Text #2

Max Range: 5.0576. Min Range: -5.0576

Max Act: 5.0576. Min Act: -0.1700

Data Index: 4875346 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9947. Min Act: -0.1700

Data Index: 2783064 (Open Web Text)

Max Activating Token Index: 963

Text #4

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9674. Min Act: -0.1700

Data Index: 5745056 (Open Web Text)

Max Activating Token Index: 467

Text #5

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9403. Min Act: -0.1700

Data Index: 3834642 (Open Web Text)

Max Activating Token Index: 304

Text #6

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9405. Min Act: -0.1700

Data Index: 7179091 (Open Web Text)

Max Activating Token Index: 974

Text #7

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9258. Min Act: -0.1700

Data Index: 5131008 (Open Web Text)

Max Activating Token Index: 774

Text #8

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9434. Min Act: -0.1700

Data Index: 2317147 (Open Web Text)

Max Activating Token Index: 192

Text #9

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9439. Min Act: -0.1700

Data Index: 2639911 (Open Web Text)

Max Activating Token Index: 616

Text #10

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9172. Min Act: -0.1700

Data Index: 427178 (Open Web Text)

Max Activating Token Index: 927

Text #11

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9337. Min Act: -0.1700

Data Index: 5044619 (Open Web Text)

Max Activating Token Index: 600

Text #12

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9009. Min Act: -0.1700

Data Index: 3291093 (Open Web Text)

Max Activating Token Index: 662

Text #13

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9043. Min Act: -0.1700

Data Index: 1623592 (Open Web Text)

Max Activating Token Index: 778

Text #14

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8760. Min Act: -0.1700

Data Index: 3391486 (Open Web Text)

Max Activating Token Index: 949

Text #15

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.9181. Min Act: -0.1700

Data Index: 1145239 (Open Web Text)

Max Activating Token Index: 806

Text #16

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8828. Min Act: -0.1700

Data Index: 514655 (Open Web Text)

Max Activating Token Index: 423

Text #17

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8693. Min Act: -0.1700

Data Index: 6502069 (Open Web Text)

Max Activating Token Index: 702

Text #18

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8632. Min Act: -0.1700

Data Index: 6325912 (Open Web Text)

Max Activating Token Index: 896

Text #19

Max Range: 5.0576. Min Range: -5.0576

Max Act: 4.8596. Min Act: -0.1700

Data Index: 7545308 (Open Web Text)

Max Activating Token Index: 300