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

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

Neuron 253 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.6970. Min Act: -0.1700

Data Index: 1540489 (Python Code)

Max Activating Token Index: 175

Text #1

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.6345. Min Act: -0.1700

Data Index: 1480383 (Python Code)

Max Activating Token Index: 120

Text #2

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5095. Min Act: -0.1700

Data Index: 1460171 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5720. Min Act: -0.1700

Data Index: 1583130 (Python Code)

Max Activating Token Index: 237

Text #4

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5408. Min Act: -0.1700

Data Index: 1613089 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5095. Min Act: -0.1700

Data Index: 1505996 (Python Code)

Max Activating Token Index: 910

Text #6

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4783. Min Act: -0.1700

Data Index: 1535697 (Python Code)

Max Activating Token Index: 878

Text #7

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5095. Min Act: -0.1700

Data Index: 1524933 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5720. Min Act: -0.1700

Data Index: 1381529 (Python Code)

Max Activating Token Index: 463

Text #9

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5408. Min Act: -0.1700

Data Index: 1582458 (Python Code)

Max Activating Token Index: 787

Text #10

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5095. Min Act: -0.1700

Data Index: 1654269 (Python Code)

Max Activating Token Index: 297

Text #11

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4158. Min Act: -0.1700

Data Index: 1556492 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4470. Min Act: -0.1700

Data Index: 1458815 (Python Code)

Max Activating Token Index: 422

Text #13

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.5095. Min Act: -0.1700

Data Index: 303422 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4783. Min Act: -0.1700

Data Index: 1647603 (Python Code)

Max Activating Token Index: 204

Text #15

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.3845. Min Act: -0.1700

Data Index: 1514337 (Python Code)

Max Activating Token Index: 305

Text #16

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4783. Min Act: -0.1700

Data Index: 1558256 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4783. Min Act: -0.1700

Data Index: 1641499 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4783. Min Act: -0.1700

Data Index: 1522754 (Python Code)

Max Activating Token Index: 67

Text #19

Max Range: 5.6970. Min Range: -5.6970

Max Act: 5.4158. Min Act: -0.1700

Data Index: 1450859 (Python Code)

Max Activating Token Index: 858