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

Dataset: Open Web Text

Neuron 278 in Layer 5

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: 4.4831. Min Range: -4.4831

Max Act: 4.4831. Min Act: -0.1700

Data Index: 8780971 (Open Web Text)

Max Activating Token Index: 625

Text #1

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.4281. Min Act: -0.1700

Data Index: 221767 (Open Web Text)

Max Activating Token Index: 982

Text #2

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.4304. Min Act: -0.1700

Data Index: 41851 (Open Web Text)

Max Activating Token Index: 877

Text #3

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.4030. Min Act: -0.1700

Data Index: 2342133 (Open Web Text)

Max Activating Token Index: 932

Text #4

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.3656. Min Act: -0.1700

Data Index: 4481385 (Open Web Text)

Max Activating Token Index: 914

Text #5

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.3848. Min Act: -0.1700

Data Index: 4682304 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.3055. Min Act: -0.1700

Data Index: 1152937 (Open Web Text)

Max Activating Token Index: 747

Text #7

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.3212. Min Act: -0.1700

Data Index: 817666 (Open Web Text)

Max Activating Token Index: 729

Text #8

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.3397. Min Act: -0.1700

Data Index: 8622986 (Open Web Text)

Max Activating Token Index: 528

Text #9

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.3405. Min Act: -0.1700

Data Index: 1942373 (Open Web Text)

Max Activating Token Index: 969

Text #10

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.3555. Min Act: -0.1700

Data Index: 8483612 (Open Web Text)

Max Activating Token Index: 611

Text #11

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.3282. Min Act: -0.1700

Data Index: 5069616 (Open Web Text)

Max Activating Token Index: 721

Text #12

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.3079. Min Act: -0.1700

Data Index: 4221599 (Open Web Text)

Max Activating Token Index: 368

Text #13

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.2736. Min Act: -0.1700

Data Index: 3346212 (Open Web Text)

Max Activating Token Index: 355

Text #14

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.2716. Min Act: -0.1700

Data Index: 7981545 (Open Web Text)

Max Activating Token Index: 220

Text #15

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.2733. Min Act: -0.1700

Data Index: 7642090 (Open Web Text)

Max Activating Token Index: 988

Text #16

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.2835. Min Act: -0.1700

Data Index: 4180042 (Open Web Text)

Max Activating Token Index: 175

Text #17

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.2526. Min Act: -0.1700

Data Index: 8421274 (Open Web Text)

Max Activating Token Index: 189

Text #18

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.2469. Min Act: -0.1700

Data Index: 1666426 (Open Web Text)

Max Activating Token Index: 883

Text #19

Max Range: 4.4831. Min Range: -4.4831

Max Act: 4.2028. Min Act: -0.1700

Data Index: 3786033 (Open Web Text)

Max Activating Token Index: 590