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

Dataset: Open Web Text

Neuron 2728 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: 3.0338. Min Range: -3.0338

Max Act: 3.0338. Min Act: -0.1700

Data Index: 8338738 (Open Web Text)

Max Activating Token Index: 472

Text #1

Max Range: 3.0338. Min Range: -3.0338

Max Act: 3.0024. Min Act: -0.1700

Data Index: 152650 (Open Web Text)

Max Activating Token Index: 192

Text #2

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9818. Min Act: -0.1700

Data Index: 201498 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9799. Min Act: -0.1700

Data Index: 287695 (Open Web Text)

Max Activating Token Index: 77

Text #4

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9841. Min Act: -0.1700

Data Index: 2039877 (Open Web Text)

Max Activating Token Index: 389

Text #5

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9652. Min Act: -0.1700

Data Index: 1687537 (Open Web Text)

Max Activating Token Index: 979

Text #6

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9674. Min Act: -0.1700

Data Index: 5658956 (Open Web Text)

Max Activating Token Index: 226

Text #7

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9579. Min Act: -0.1700

Data Index: 7620139 (Open Web Text)

Max Activating Token Index: 259

Text #8

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9672. Min Act: -0.1700

Data Index: 6904764 (Open Web Text)

Max Activating Token Index: 528

Text #9

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9705. Min Act: -0.1700

Data Index: 2305664 (Open Web Text)

Max Activating Token Index: 923

Text #10

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9707. Min Act: -0.1700

Data Index: 5176370 (Open Web Text)

Max Activating Token Index: 654

Text #11

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9487. Min Act: -0.1700

Data Index: 8146030 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9398. Min Act: -0.1700

Data Index: 4304196 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9356. Min Act: -0.1700

Data Index: 6780360 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9405. Min Act: -0.1700

Data Index: 1558162 (Open Web Text)

Max Activating Token Index: 852

Text #15

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9103. Min Act: -0.1700

Data Index: 1887410 (Open Web Text)

Max Activating Token Index: 1012

Text #16

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9371. Min Act: -0.1700

Data Index: 2819925 (Open Web Text)

Max Activating Token Index: 701

Text #17

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9264. Min Act: -0.1700

Data Index: 4014976 (Open Web Text)

Max Activating Token Index: 70

Text #18

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9352. Min Act: -0.1700

Data Index: 5597239 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 3.0338. Min Range: -3.0338

Max Act: 2.9331. Min Act: -0.1700

Data Index: 2840529 (Open Web Text)

Max Activating Token Index: 1019