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

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

Neuron 656 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: 3.5880. Min Range: -3.5880

Max Act: 3.5880. Min Act: -0.1700

Data Index: 497438 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.5254. Min Act: -0.1700

Data Index: 889333 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.4560. Min Act: -0.1700

Data Index: 237318 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.4164. Min Act: -0.1700

Data Index: 38071 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.4020. Min Act: -0.1700

Data Index: 1157217 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.3638. Min Act: -0.1700

Data Index: 734077 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.3765. Min Act: -0.1700

Data Index: 124331 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.3413. Min Act: -0.1700

Data Index: 617544 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.3545. Min Act: -0.1700

Data Index: 112317 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.3034. Min Act: -0.1700

Data Index: 69765 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.2819. Min Act: -0.1700

Data Index: 1088252 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.2799. Min Act: -0.1700

Data Index: 594534 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.2890. Min Act: -0.1700

Data Index: 101066 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.2621. Min Act: -0.1700

Data Index: 109612 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.2427. Min Act: -0.1700

Data Index: 631874 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.2458. Min Act: -0.1700

Data Index: 567410 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.2438. Min Act: -0.1700

Data Index: 847617 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.2395. Min Act: -0.1700

Data Index: 972047 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.2373. Min Act: -0.1700

Data Index: 728179 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 3.5880. Min Range: -3.5880

Max Act: 3.2437. Min Act: -0.1700

Data Index: 424375 (C4 (Web Text))

Max Activating Token Index: 244