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

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

Neuron 1605 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: 3.8026. Min Range: -3.8026

Max Act: 3.7714. Min Act: -0.1700

Data Index: 520654 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.8026. Min Act: -0.1700

Data Index: 1201673 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.7088. Min Act: -0.1700

Data Index: 64972 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.6462. Min Act: -0.1700

Data Index: 861356 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.6149. Min Act: -0.1700

Data Index: 157484 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.5522. Min Act: -0.1700

Data Index: 368424 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.5209. Min Act: -0.1700

Data Index: 754448 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.4896. Min Act: -0.1700

Data Index: 54865 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.5209. Min Act: -0.1700

Data Index: 1012216 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.4896. Min Act: -0.1700

Data Index: 533253 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.4896. Min Act: -0.1700

Data Index: 568317 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.4896. Min Act: -0.1700

Data Index: 489192 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.4582. Min Act: -0.1700

Data Index: 747869 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.4582. Min Act: -0.1700

Data Index: 36650 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.4896. Min Act: -0.1700

Data Index: 380635 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.4582. Min Act: -0.1700

Data Index: 807611 (C4 (Web Text))

Max Activating Token Index: 439

Text #16

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.4269. Min Act: -0.1700

Data Index: 701342 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.4896. Min Act: -0.1700

Data Index: 1319771 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.3955. Min Act: -0.1700

Data Index: 7481 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 3.8026. Min Range: -3.8026

Max Act: 3.4269. Min Act: -0.1700

Data Index: 1070371 (C4 (Web Text))

Max Activating Token Index: 829