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

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

Neuron 323 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: 3.2485. Min Range: -3.2485

Max Act: 3.2485. Min Act: -0.1700

Data Index: 1154737 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 3.2485. Min Range: -3.2485

Max Act: 3.1047. Min Act: -0.1700

Data Index: 866919 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 3.2485. Min Range: -3.2485

Max Act: 3.0346. Min Act: -0.1700

Data Index: 1147955 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 3.2485. Min Range: -3.2485

Max Act: 3.0524. Min Act: -0.1700

Data Index: 113726 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 3.2485. Min Range: -3.2485

Max Act: 3.0520. Min Act: -0.1700

Data Index: 159043 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 3.2485. Min Range: -3.2485

Max Act: 3.0361. Min Act: -0.1700

Data Index: 923648 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 3.2485. Min Range: -3.2485

Max Act: 3.0096. Min Act: -0.1700

Data Index: 713850 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 3.2485. Min Range: -3.2485

Max Act: 3.0105. Min Act: -0.1700

Data Index: 1153123 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.9958. Min Act: -0.1700

Data Index: 348734 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 3.2485. Min Range: -3.2485

Max Act: 3.0079. Min Act: -0.1700

Data Index: 899172 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.9951. Min Act: -0.1700

Data Index: 802310 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.9903. Min Act: -0.1700

Data Index: 1080749 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.9846. Min Act: -0.1700

Data Index: 881379 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.9704. Min Act: -0.1700

Data Index: 1191988 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.9690. Min Act: -0.1699

Data Index: 381218 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.9725. Min Act: -0.1700

Data Index: 171631 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.9423. Min Act: -0.1700

Data Index: 237827 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.9513. Min Act: -0.1700

Data Index: 377212 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.9382. Min Act: -0.1700

Data Index: 1264985 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 3.2485. Min Range: -3.2485

Max Act: 2.9295. Min Act: -0.1700

Data Index: 414215 (C4 (Web Text))

Max Activating Token Index: 183