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

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

Neuron 1322 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: 3.8797. Min Range: -3.8797

Max Act: 3.8797. Min Act: -0.1700

Data Index: 664924 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.8588. Min Act: -0.1700

Data Index: 17119 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.8280. Min Act: -0.1700

Data Index: 1403555 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.8164. Min Act: -0.1700

Data Index: 83724 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.8286. Min Act: -0.1700

Data Index: 1140115 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.7951. Min Act: -0.1700

Data Index: 1050760 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.7756. Min Act: -0.1700

Data Index: 305382 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.7467. Min Act: -0.1700

Data Index: 162707 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.7204. Min Act: -0.1700

Data Index: 752161 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.7514. Min Act: -0.1700

Data Index: 454320 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.7647. Min Act: -0.1700

Data Index: 476589 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.7335. Min Act: -0.1700

Data Index: 1378155 (Python Code)

Max Activating Token Index: 141

Text #12

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.7427. Min Act: -0.1700

Data Index: 841955 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.6737. Min Act: -0.1700

Data Index: 58135 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.6966. Min Act: -0.1700

Data Index: 954990 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.7079. Min Act: -0.1700

Data Index: 1084938 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.7191. Min Act: -0.1700

Data Index: 1595694 (Python Code)

Max Activating Token Index: 259

Text #17

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.7082. Min Act: -0.1700

Data Index: 1524880 (Python Code)

Max Activating Token Index: 344

Text #18

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.6873. Min Act: -0.1700

Data Index: 289089 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 3.8797. Min Range: -3.8797

Max Act: 3.6825. Min Act: -0.1700

Data Index: 1120842 (C4 (Web Text))

Max Activating Token Index: 49