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

Dataset: Open Web Text

Neuron 628 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: 3.6224. Min Range: -3.6224

Max Act: 3.6224. Min Act: -0.1700

Data Index: 8070717 (Open Web Text)

Max Activating Token Index: 70

Text #1

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.5295. Min Act: -0.1700

Data Index: 7803558 (Open Web Text)

Max Activating Token Index: 561

Text #2

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.5358. Min Act: -0.1700

Data Index: 1611251 (Open Web Text)

Max Activating Token Index: 84

Text #3

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.5369. Min Act: -0.1700

Data Index: 7978845 (Open Web Text)

Max Activating Token Index: 397

Text #4

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4943. Min Act: -0.1700

Data Index: 3864281 (Open Web Text)

Max Activating Token Index: 832

Text #5

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4916. Min Act: -0.1700

Data Index: 2062544 (Open Web Text)

Max Activating Token Index: 111

Text #6

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4493. Min Act: -0.1700

Data Index: 4200974 (Open Web Text)

Max Activating Token Index: 918

Text #7

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.5094. Min Act: -0.1700

Data Index: 4128282 (Open Web Text)

Max Activating Token Index: 877

Text #8

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4335. Min Act: -0.1700

Data Index: 2990664 (Open Web Text)

Max Activating Token Index: 291

Text #9

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4665. Min Act: -0.1700

Data Index: 7692233 (Open Web Text)

Max Activating Token Index: 852

Text #10

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4637. Min Act: -0.1700

Data Index: 2155782 (Open Web Text)

Max Activating Token Index: 663

Text #11

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4294. Min Act: -0.1700

Data Index: 6065161 (Open Web Text)

Max Activating Token Index: 468

Text #12

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4382. Min Act: -0.1700

Data Index: 4252780 (Open Web Text)

Max Activating Token Index: 784

Text #13

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4232. Min Act: -0.1700

Data Index: 7364897 (Open Web Text)

Max Activating Token Index: 632

Text #14

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4078. Min Act: -0.1700

Data Index: 7884571 (Open Web Text)

Max Activating Token Index: 449

Text #15

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4205. Min Act: -0.1700

Data Index: 2087178 (Open Web Text)

Max Activating Token Index: 117

Text #16

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4347. Min Act: -0.1700

Data Index: 2355979 (Open Web Text)

Max Activating Token Index: 730

Text #17

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4027. Min Act: -0.1700

Data Index: 3270095 (Open Web Text)

Max Activating Token Index: 304

Text #18

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4248. Min Act: -0.1700

Data Index: 7747785 (Open Web Text)

Max Activating Token Index: 124

Text #19

Max Range: 3.6224. Min Range: -3.6224

Max Act: 3.4354. Min Act: -0.1700

Data Index: 1195027 (Open Web Text)

Max Activating Token Index: 695