Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1097 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.6161. Min Act: -0.1700

Data Index: 1012098 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.5222. Min Act: -0.1700

Data Index: 1256861 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.4595. Min Act: -0.1700

Data Index: 1247711 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.4752. Min Act: -0.1700

Data Index: 900493 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.4595. Min Act: -0.1700

Data Index: 888879 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.4595. Min Act: -0.1700

Data Index: 440599 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.4438. Min Act: -0.1700

Data Index: 434413 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.4281. Min Act: -0.1700

Data Index: 1234414 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.4438. Min Act: -0.1700

Data Index: 86421 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.4281. Min Act: -0.1700

Data Index: 244670 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.3968. Min Act: -0.1700

Data Index: 1158034 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.3968. Min Act: -0.1700

Data Index: 663362 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.3654. Min Act: -0.1700

Data Index: 166904 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.3497. Min Act: -0.1700

Data Index: 411545 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.3183. Min Act: -0.1700

Data Index: 1261398 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.3183. Min Act: -0.1700

Data Index: 1114866 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.3497. Min Act: -0.1700

Data Index: 841965 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.3340. Min Act: -0.1700

Data Index: 330640 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.3497. Min Act: -0.1700

Data Index: 239277 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 3.6161. Min Range: -3.6161

Max Act: 3.3654. Min Act: -0.1700

Data Index: 1330137 (C4 (Web Text))

Max Activating Token Index: 775