Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 397 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.2303. Min Range: -3.2303

Max Act: 3.2303. Min Act: -0.1700

Data Index: 325393 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 3.2303. Min Range: -3.2303

Max Act: 3.1527. Min Act: -0.1700

Data Index: 895237 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 3.2303. Min Range: -3.2303

Max Act: 3.1322. Min Act: -0.1700

Data Index: 977726 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 3.2303. Min Range: -3.2303

Max Act: 3.1080. Min Act: -0.1700

Data Index: 1509424 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 3.2303. Min Range: -3.2303

Max Act: 3.0686. Min Act: -0.1700

Data Index: 583418 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 3.2303. Min Range: -3.2303

Max Act: 3.0314. Min Act: -0.1700

Data Index: 353335 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 3.2303. Min Range: -3.2303

Max Act: 3.0310. Min Act: -0.1700

Data Index: 424248 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 3.2303. Min Range: -3.2303

Max Act: 2.9990. Min Act: -0.1700

Data Index: 832190 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 3.2303. Min Range: -3.2303

Max Act: 3.0260. Min Act: -0.1700

Data Index: 1171067 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 3.2303. Min Range: -3.2303

Max Act: 2.9993. Min Act: -0.1700

Data Index: 1112641 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 3.2303. Min Range: -3.2303

Max Act: 3.0065. Min Act: -0.1700

Data Index: 1060893 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 3.2303. Min Range: -3.2303

Max Act: 2.9864. Min Act: -0.1700

Data Index: 956816 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 3.2303. Min Range: -3.2303

Max Act: 3.0023. Min Act: -0.1700

Data Index: 70495 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 3.2303. Min Range: -3.2303

Max Act: 3.0000. Min Act: -0.1700

Data Index: 161328 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 3.2303. Min Range: -3.2303

Max Act: 2.9887. Min Act: -0.1700

Data Index: 1305975 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 3.2303. Min Range: -3.2303

Max Act: 2.9941. Min Act: -0.1700

Data Index: 1349055 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 3.2303. Min Range: -3.2303

Max Act: 2.9788. Min Act: -0.1700

Data Index: 70391 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 3.2303. Min Range: -3.2303

Max Act: 2.9728. Min Act: -0.1700

Data Index: 1179408 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 3.2303. Min Range: -3.2303

Max Act: 2.9816. Min Act: -0.1700

Data Index: 1210519 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 3.2303. Min Range: -3.2303

Max Act: 2.9770. Min Act: -0.1700

Data Index: 190383 (C4 (Web Text))

Max Activating Token Index: 433