Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1376 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 13.0150. Min Range: -13.0150

Max Act: 13.0150. Min Act: -0.1699

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 13.0150. Min Range: -13.0150

Max Act: 12.1171. Min Act: -0.1700

Data Index: 1643779 (Python Code)

Max Activating Token Index: 670

Text #2

Max Range: 13.0150. Min Range: -13.0150

Max Act: 12.0221. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 13.0150. Min Range: -13.0150

Max Act: 11.9678. Min Act: -0.1700

Data Index: 955345 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 13.0150. Min Range: -13.0150

Max Act: 11.8140. Min Act: -0.1700

Data Index: 1483328 (Python Code)

Max Activating Token Index: 817

Text #5

Max Range: 13.0150. Min Range: -13.0150

Max Act: 11.5860. Min Act: -0.1700

Data Index: 1601652 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 13.0150. Min Range: -13.0150

Max Act: 11.2834. Min Act: -0.1700

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 13.0150. Min Range: -13.0150

Max Act: 11.2368. Min Act: -0.1700

Data Index: 422235 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 13.0150. Min Range: -13.0150

Max Act: 11.0520. Min Act: -0.1699

Data Index: 1641948 (Python Code)

Max Activating Token Index: 395

Text #9

Max Range: 13.0150. Min Range: -13.0150

Max Act: 11.0564. Min Act: -0.1700

Data Index: 1656685 (Python Code)

Max Activating Token Index: 205

Text #10

Max Range: 13.0150. Min Range: -13.0150

Max Act: 11.0159. Min Act: -0.1700

Data Index: 1213837 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 13.0150. Min Range: -13.0150

Max Act: 10.8249. Min Act: -0.1700

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 13.0150. Min Range: -13.0150

Max Act: 10.8962. Min Act: -0.1700

Data Index: 1556465 (Python Code)

Max Activating Token Index: 85

Text #13

Max Range: 13.0150. Min Range: -13.0150

Max Act: 10.8270. Min Act: -0.1700

Data Index: 1439139 (Python Code)

Max Activating Token Index: 989

Text #14

Max Range: 13.0150. Min Range: -13.0150

Max Act: 10.8167. Min Act: -0.1700

Data Index: 1412933 (Python Code)

Max Activating Token Index: 378

Text #15

Max Range: 13.0150. Min Range: -13.0150

Max Act: 10.7716. Min Act: -0.1700

Data Index: 1601263 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 13.0150. Min Range: -13.0150

Max Act: 10.7542. Min Act: -0.1699

Data Index: 1548039 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 13.0150. Min Range: -13.0150

Max Act: 10.7551. Min Act: -0.1700

Data Index: 1506777 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 13.0150. Min Range: -13.0150

Max Act: 10.6522. Min Act: -0.1700

Data Index: 1535151 (Python Code)

Max Activating Token Index: 273

Text #19

Max Range: 13.0150. Min Range: -13.0150

Max Act: 10.6174. Min Act: -0.1700

Data Index: 1649474 (Python Code)

Max Activating Token Index: 805