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

Dataset: Open Web Text

Neuron 2028 in Layer 1

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: 3.2609. Min Range: -3.2609

Max Act: 3.2609. Min Act: -0.1700

Data Index: 8067889 (Open Web Text)

Max Activating Token Index: 46

Text #1

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.2505. Min Act: -0.1700

Data Index: 6349166 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.2291. Min Act: -0.1700

Data Index: 7820655 (Open Web Text)

Max Activating Token Index: 62

Text #3

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.2325. Min Act: -0.1700

Data Index: 7043096 (Open Web Text)

Max Activating Token Index: 224

Text #4

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.2071. Min Act: -0.1700

Data Index: 6011243 (Open Web Text)

Max Activating Token Index: 101

Text #5

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.2073. Min Act: -0.1700

Data Index: 3616203 (Open Web Text)

Max Activating Token Index: 238

Text #6

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1922. Min Act: -0.1700

Data Index: 5483441 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.2089. Min Act: -0.1700

Data Index: 8722572 (Open Web Text)

Max Activating Token Index: 620

Text #8

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1861. Min Act: -0.1700

Data Index: 4659351 (Open Web Text)

Max Activating Token Index: 326

Text #9

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1805. Min Act: -0.1700

Data Index: 5116363 (Open Web Text)

Max Activating Token Index: 304

Text #10

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1613. Min Act: -0.1700

Data Index: 915288 (Open Web Text)

Max Activating Token Index: 33

Text #11

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1572. Min Act: -0.1700

Data Index: 3057518 (Open Web Text)

Max Activating Token Index: 237

Text #12

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1751. Min Act: -0.1700

Data Index: 2866294 (Open Web Text)

Max Activating Token Index: 425

Text #13

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1487. Min Act: -0.1700

Data Index: 6242952 (Open Web Text)

Max Activating Token Index: 68

Text #14

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1531. Min Act: -0.1700

Data Index: 118438 (Open Web Text)

Max Activating Token Index: 79

Text #15

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1371. Min Act: -0.1700

Data Index: 3232701 (Open Web Text)

Max Activating Token Index: 97

Text #16

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1380. Min Act: -0.1700

Data Index: 576837 (Open Web Text)

Max Activating Token Index: 204

Text #17

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1220. Min Act: -0.1700

Data Index: 2231524 (Open Web Text)

Max Activating Token Index: 141

Text #18

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1230. Min Act: -0.1700

Data Index: 2926771 (Open Web Text)

Max Activating Token Index: 147

Text #19

Max Range: 3.2609. Min Range: -3.2609

Max Act: 3.1413. Min Act: -0.1700

Data Index: 3742195 (Open Web Text)

Max Activating Token Index: 222