Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 229 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1137. Min Range: -3.1137

Max Act: 3.1137. Min Act: -0.1700

Data Index: 743824 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 3.1137. Min Range: -3.1137

Max Act: 3.0190. Min Act: -0.1700

Data Index: 354548 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.9399. Min Act: -0.1700

Data Index: 1605142 (Python Code)

Max Activating Token Index: 660

Text #3

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.9715. Min Act: -0.1700

Data Index: 579134 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.9240. Min Act: -0.1700

Data Index: 292293 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8764. Min Act: -0.1700

Data Index: 1474361 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8606. Min Act: -0.1700

Data Index: 167691 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8764. Min Act: -0.1700

Data Index: 762160 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8606. Min Act: -0.1700

Data Index: 1556147 (Python Code)

Max Activating Token Index: 842

Text #9

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8606. Min Act: -0.1700

Data Index: 141438 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8606. Min Act: -0.1700

Data Index: 848594 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8288. Min Act: -0.1700

Data Index: 379504 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.7969. Min Act: -0.1700

Data Index: 175269 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8606. Min Act: -0.1700

Data Index: 1211777 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8764. Min Act: -0.1700

Data Index: 246334 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8606. Min Act: -0.1700

Data Index: 936575 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8606. Min Act: -0.1700

Data Index: 1181429 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8447. Min Act: -0.1700

Data Index: 281114 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.7491. Min Act: -0.1700

Data Index: 1265109 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 3.1137. Min Range: -3.1137

Max Act: 2.8764. Min Act: -0.1700

Data Index: 1212877 (C4 (Web Text))

Max Activating Token Index: 770