Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2037 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1494. Min Range: -3.1494

Max Act: 3.1494. Min Act: -0.1700

Data Index: 744209 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 3.1494. Min Range: -3.1494

Max Act: 3.1179. Min Act: -0.1700

Data Index: 953839 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 3.1494. Min Range: -3.1494

Max Act: 3.1179. Min Act: -0.1700

Data Index: 995842 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 3.1494. Min Range: -3.1494

Max Act: 3.0074. Min Act: -0.1700

Data Index: 513401 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 3.1494. Min Range: -3.1494

Max Act: 3.0074. Min Act: -0.1700

Data Index: 1090037 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9916. Min Act: -0.1700

Data Index: 1180709 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9758. Min Act: -0.1700

Data Index: 1302599 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9599. Min Act: -0.1700

Data Index: 1090533 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9599. Min Act: -0.1700

Data Index: 400939 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9283. Min Act: -0.1700

Data Index: 1292312 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9124. Min Act: -0.1700

Data Index: 191250 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9283. Min Act: -0.1700

Data Index: 102950 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9124. Min Act: -0.1700

Data Index: 676098 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9283. Min Act: -0.1700

Data Index: 611858 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9283. Min Act: -0.1700

Data Index: 503847 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9283. Min Act: -0.1700

Data Index: 916492 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9124. Min Act: -0.1700

Data Index: 147765 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9124. Min Act: -0.1700

Data Index: 216121 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.8965. Min Act: -0.1700

Data Index: 765053 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 3.1494. Min Range: -3.1494

Max Act: 2.9124. Min Act: -0.1700

Data Index: 902413 (C4 (Web Text))

Max Activating Token Index: 454