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

Dataset: Open Web Text

Neuron 2447 in Layer 6

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: 5.2264. Min Range: -5.2264

Max Act: 5.1993. Min Act: -0.1700

Data Index: 2125083 (Open Web Text)

Max Activating Token Index: 370

Text #1

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.2264. Min Act: -0.1700

Data Index: 192282 (Open Web Text)

Max Activating Token Index: 924

Text #2

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.1643. Min Act: -0.1700

Data Index: 4684711 (Open Web Text)

Max Activating Token Index: 752

Text #3

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.1362. Min Act: -0.1700

Data Index: 1319225 (Open Web Text)

Max Activating Token Index: 486

Text #4

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.0593. Min Act: -0.1700

Data Index: 1132630 (Open Web Text)

Max Activating Token Index: 243

Text #5

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.0570. Min Act: -0.1700

Data Index: 3791439 (Open Web Text)

Max Activating Token Index: 300

Text #6

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.0861. Min Act: -0.1700

Data Index: 5105306 (Open Web Text)

Max Activating Token Index: 230

Text #7

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.0862. Min Act: -0.1700

Data Index: 2073853 (Open Web Text)

Max Activating Token Index: 299

Text #8

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.0163. Min Act: -0.1700

Data Index: 4834644 (Open Web Text)

Max Activating Token Index: 641

Text #9

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.0257. Min Act: -0.1700

Data Index: 1270413 (Open Web Text)

Max Activating Token Index: 288

Text #10

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.0303. Min Act: -0.1700

Data Index: 7303438 (Open Web Text)

Max Activating Token Index: 503

Text #11

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.0248. Min Act: -0.1700

Data Index: 3666972 (Open Web Text)

Max Activating Token Index: 566

Text #12

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.0300. Min Act: -0.1700

Data Index: 4414402 (Open Web Text)

Max Activating Token Index: 253

Text #13

Max Range: 5.2264. Min Range: -5.2264

Max Act: 4.9950. Min Act: -0.1700

Data Index: 4637487 (Open Web Text)

Max Activating Token Index: 926

Text #14

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.0092. Min Act: -0.1700

Data Index: 8483281 (Open Web Text)

Max Activating Token Index: 989

Text #15

Max Range: 5.2264. Min Range: -5.2264

Max Act: 4.9968. Min Act: -0.1700

Data Index: 7321487 (Open Web Text)

Max Activating Token Index: 294

Text #16

Max Range: 5.2264. Min Range: -5.2264

Max Act: 5.0092. Min Act: -0.1700

Data Index: 1019464 (Open Web Text)

Max Activating Token Index: 461

Text #17

Max Range: 5.2264. Min Range: -5.2264

Max Act: 4.9982. Min Act: -0.1700

Data Index: 4446811 (Open Web Text)

Max Activating Token Index: 323

Text #18

Max Range: 5.2264. Min Range: -5.2264

Max Act: 4.9834. Min Act: -0.1700

Data Index: 4993966 (Open Web Text)

Max Activating Token Index: 607

Text #19

Max Range: 5.2264. Min Range: -5.2264

Max Act: 4.9709. Min Act: -0.1700

Data Index: 5139234 (Open Web Text)

Max Activating Token Index: 344