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

Dataset: Open Web Text

Neuron 891 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: 3.9179. Min Range: -3.9179

Max Act: 3.9179. Min Act: -0.1700

Data Index: 4971844 (Open Web Text)

Max Activating Token Index: 873

Text #1

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8900. Min Act: -0.1700

Data Index: 549444 (Open Web Text)

Max Activating Token Index: 972

Text #2

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8799. Min Act: -0.1700

Data Index: 8616724 (Open Web Text)

Max Activating Token Index: 969

Text #3

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8762. Min Act: -0.1700

Data Index: 6335589 (Open Web Text)

Max Activating Token Index: 616

Text #4

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8633. Min Act: -0.1700

Data Index: 3380787 (Open Web Text)

Max Activating Token Index: 279

Text #5

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8286. Min Act: -0.1700

Data Index: 5053475 (Open Web Text)

Max Activating Token Index: 829

Text #6

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8102. Min Act: -0.1700

Data Index: 8177638 (Open Web Text)

Max Activating Token Index: 529

Text #7

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8256. Min Act: -0.1700

Data Index: 3755915 (Open Web Text)

Max Activating Token Index: 555

Text #8

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7917. Min Act: -0.1700

Data Index: 6393238 (Open Web Text)

Max Activating Token Index: 953

Text #9

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8122. Min Act: -0.1700

Data Index: 1467984 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8049. Min Act: -0.1700

Data Index: 4421072 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7835. Min Act: -0.1700

Data Index: 1996304 (Open Web Text)

Max Activating Token Index: 957

Text #12

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7965. Min Act: -0.1700

Data Index: 6425805 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.8081. Min Act: -0.1700

Data Index: 4890528 (Open Web Text)

Max Activating Token Index: 296

Text #14

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7816. Min Act: -0.1700

Data Index: 7723374 (Open Web Text)

Max Activating Token Index: 1005

Text #15

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7973. Min Act: -0.1700

Data Index: 8038116 (Open Web Text)

Max Activating Token Index: 999

Text #16

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7489. Min Act: -0.1700

Data Index: 4939199 (Open Web Text)

Max Activating Token Index: 599

Text #17

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7722. Min Act: -0.1700

Data Index: 4941391 (Open Web Text)

Max Activating Token Index: 965

Text #18

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7665. Min Act: -0.1700

Data Index: 7794442 (Open Web Text)

Max Activating Token Index: 801

Text #19

Max Range: 3.9179. Min Range: -3.9179

Max Act: 3.7519. Min Act: -0.1700

Data Index: 3276668 (Open Web Text)

Max Activating Token Index: 514