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

Dataset: Open Web Text

Neuron 1548 in Layer 0

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: 4.2317. Min Range: -4.2317

Max Act: 4.2317. Min Act: -0.1700

Data Index: 5029583 (Open Web Text)

Max Activating Token Index: 523

Text #1

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.1125. Min Act: -0.1700

Data Index: 7797365 (Open Web Text)

Max Activating Token Index: 527

Text #2

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0729. Min Act: -0.1700

Data Index: 5019656 (Open Web Text)

Max Activating Token Index: 913

Text #3

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0592. Min Act: -0.1700

Data Index: 1597378 (Open Web Text)

Max Activating Token Index: 362

Text #4

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0842. Min Act: -0.1700

Data Index: 3560467 (Open Web Text)

Max Activating Token Index: 84

Text #5

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0374. Min Act: -0.1700

Data Index: 2191097 (Open Web Text)

Max Activating Token Index: 251

Text #6

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0215. Min Act: -0.1700

Data Index: 3595382 (Open Web Text)

Max Activating Token Index: 673

Text #7

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0467. Min Act: -0.1700

Data Index: 353056 (Open Web Text)

Max Activating Token Index: 453

Text #8

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0311. Min Act: -0.1700

Data Index: 589204 (Open Web Text)

Max Activating Token Index: 851

Text #9

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0024. Min Act: -0.1700

Data Index: 3392947 (Open Web Text)

Max Activating Token Index: 49

Text #10

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0057. Min Act: -0.1700

Data Index: 8694089 (Open Web Text)

Max Activating Token Index: 464

Text #11

Max Range: 4.2317. Min Range: -4.2317

Max Act: 3.9986. Min Act: -0.1700

Data Index: 8656737 (Open Web Text)

Max Activating Token Index: 453

Text #12

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0200. Min Act: -0.1700

Data Index: 2719317 (Open Web Text)

Max Activating Token Index: 606

Text #13

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0324. Min Act: -0.1700

Data Index: 2235771 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.2317. Min Range: -4.2317

Max Act: 3.9963. Min Act: -0.1700

Data Index: 4128198 (Open Web Text)

Max Activating Token Index: 128

Text #15

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0195. Min Act: -0.1700

Data Index: 292658 (Open Web Text)

Max Activating Token Index: 421

Text #16

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0140. Min Act: -0.1700

Data Index: 951555 (Open Web Text)

Max Activating Token Index: 320

Text #17

Max Range: 4.2317. Min Range: -4.2317

Max Act: 4.0159. Min Act: -0.1700

Data Index: 1998141 (Open Web Text)

Max Activating Token Index: 803

Text #18

Max Range: 4.2317. Min Range: -4.2317

Max Act: 3.9685. Min Act: -0.1700

Data Index: 1384279 (Open Web Text)

Max Activating Token Index: 203

Text #19

Max Range: 4.2317. Min Range: -4.2317

Max Act: 3.9804. Min Act: -0.1700

Data Index: 1998158 (Open Web Text)

Max Activating Token Index: 643