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

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

Neuron 205 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: 3.3870. Min Range: -3.3870

Max Act: 3.3870. Min Act: -0.1700

Data Index: 623623 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.3770. Min Act: -0.1700

Data Index: 965443 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.3513. Min Act: -0.1700

Data Index: 498086 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.3301. Min Act: -0.1700

Data Index: 1096735 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2906. Min Act: -0.1700

Data Index: 160256 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2951. Min Act: -0.1700

Data Index: 763419 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2778. Min Act: -0.1700

Data Index: 1342836 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2487. Min Act: -0.1700

Data Index: 299197 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2546. Min Act: -0.1700

Data Index: 131161 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2674. Min Act: -0.1700

Data Index: 726148 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2449. Min Act: -0.1700

Data Index: 1311202 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2450. Min Act: -0.1700

Data Index: 814409 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2508. Min Act: -0.1700

Data Index: 418177 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2137. Min Act: -0.1700

Data Index: 348745 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2309. Min Act: -0.1700

Data Index: 94967 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.2058. Min Act: -0.1700

Data Index: 1329486 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.1897. Min Act: -0.1700

Data Index: 538560 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.1995. Min Act: -0.1700

Data Index: 17130 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.1710. Min Act: -0.1700

Data Index: 406072 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.3870. Min Range: -3.3870

Max Act: 3.1788. Min Act: -0.1700

Data Index: 1308573 (C4 (Web Text))

Max Activating Token Index: 236