Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1254 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.8482. Min Act: -0.1700

Data Index: 109672 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.7856. Min Act: -0.1700

Data Index: 502431 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.6605. Min Act: -0.1700

Data Index: 372407 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.6292. Min Act: -0.1700

Data Index: 768410 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.6292. Min Act: -0.1700

Data Index: 226503 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5665. Min Act: -0.1700

Data Index: 1334145 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5979. Min Act: -0.1700

Data Index: 1087470 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5665. Min Act: -0.1700

Data Index: 523072 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5665. Min Act: -0.1700

Data Index: 408414 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5352. Min Act: -0.1700

Data Index: 509696 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5352. Min Act: -0.1700

Data Index: 567423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5352. Min Act: -0.1700

Data Index: 949374 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5352. Min Act: -0.1700

Data Index: 1322279 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5352. Min Act: -0.1700

Data Index: 624166 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5352. Min Act: -0.1700

Data Index: 1075720 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5039. Min Act: -0.1700

Data Index: 262162 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5039. Min Act: -0.1700

Data Index: 583665 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5039. Min Act: -0.1700

Data Index: 473970 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5039. Min Act: -0.1700

Data Index: 938355 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.8482. Min Range: -3.8482

Max Act: 3.5039. Min Act: -0.1700

Data Index: 902725 (C4 (Web Text))

Max Activating Token Index: 1023