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

Dataset: Open Web Text

Neuron 901 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: 3.2972. Min Range: -3.2972

Max Act: 3.2972. Min Act: -0.1700

Data Index: 2300207 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 3.2972. Min Range: -3.2972

Max Act: 3.0784. Min Act: -0.1700

Data Index: 2925546 (Open Web Text)

Max Activating Token Index: 365

Text #2

Max Range: 3.2972. Min Range: -3.2972

Max Act: 3.0573. Min Act: -0.1700

Data Index: 156969 (Open Web Text)

Max Activating Token Index: 380

Text #3

Max Range: 3.2972. Min Range: -3.2972

Max Act: 3.0421. Min Act: -0.1700

Data Index: 646530 (Open Web Text)

Max Activating Token Index: 885

Text #4

Max Range: 3.2972. Min Range: -3.2972

Max Act: 3.0208. Min Act: -0.1700

Data Index: 4889520 (Open Web Text)

Max Activating Token Index: 545

Text #5

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9568. Min Act: -0.1700

Data Index: 5557149 (Open Web Text)

Max Activating Token Index: 805

Text #6

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9440. Min Act: -0.1700

Data Index: 1992427 (Open Web Text)

Max Activating Token Index: 687

Text #7

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9528. Min Act: -0.1700

Data Index: 2237724 (Open Web Text)

Max Activating Token Index: 615

Text #8

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9453. Min Act: -0.1700

Data Index: 4509316 (Open Web Text)

Max Activating Token Index: 696

Text #9

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9559. Min Act: -0.1700

Data Index: 6414246 (Open Web Text)

Max Activating Token Index: 877

Text #10

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9377. Min Act: -0.1700

Data Index: 1424561 (Open Web Text)

Max Activating Token Index: 451

Text #11

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9332. Min Act: -0.1700

Data Index: 1581798 (Open Web Text)

Max Activating Token Index: 83

Text #12

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9137. Min Act: -0.1700

Data Index: 5485045 (Open Web Text)

Max Activating Token Index: 682

Text #13

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9075. Min Act: -0.1700

Data Index: 2446378 (Open Web Text)

Max Activating Token Index: 276

Text #14

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9050. Min Act: -0.1700

Data Index: 8185013 (Open Web Text)

Max Activating Token Index: 748

Text #15

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9127. Min Act: -0.1700

Data Index: 5695271 (Open Web Text)

Max Activating Token Index: 63

Text #16

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9093. Min Act: -0.1700

Data Index: 1413360 (Open Web Text)

Max Activating Token Index: 917

Text #17

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.8814. Min Act: -0.1700

Data Index: 4608954 (Open Web Text)

Max Activating Token Index: 352

Text #18

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.8995. Min Act: -0.1700

Data Index: 6541192 (Open Web Text)

Max Activating Token Index: 748

Text #19

Max Range: 3.2972. Min Range: -3.2972

Max Act: 2.9058. Min Act: -0.1700

Data Index: 6337635 (Open Web Text)

Max Activating Token Index: 586