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

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

Neuron 54 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.7159. Min Act: -0.1700

Data Index: 1061972 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.6690. Min Act: -0.1700

Data Index: 82678 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.6220. Min Act: -0.1700

Data Index: 466500 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.6533. Min Act: -0.1700

Data Index: 311825 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.6064. Min Act: -0.1700

Data Index: 352519 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.6220. Min Act: -0.1700

Data Index: 216201 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.5281. Min Act: -0.1700

Data Index: 1505536 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.5907. Min Act: -0.1700

Data Index: 1061366 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.5437. Min Act: -0.1700

Data Index: 987304 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.5594. Min Act: -0.1700

Data Index: 446852 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.5281. Min Act: -0.1700

Data Index: 769228 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.5124. Min Act: -0.1700

Data Index: 727239 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.5124. Min Act: -0.1700

Data Index: 382656 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.5281. Min Act: -0.1700

Data Index: 1282173 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.5281. Min Act: -0.1700

Data Index: 235856 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.5281. Min Act: -0.1700

Data Index: 795856 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.4967. Min Act: -0.1700

Data Index: 1195979 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.4967. Min Act: -0.1700

Data Index: 555067 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.5124. Min Act: -0.1700

Data Index: 290358 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 3.7159. Min Range: -3.7159

Max Act: 3.4810. Min Act: -0.1700

Data Index: 1334062 (C4 (Web Text))

Max Activating Token Index: 650