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

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

Neuron 956 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.4247. Min Act: -0.1700

Data Index: 133331 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.4247. Min Act: -0.1700

Data Index: 1049241 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.3933. Min Act: -0.1700

Data Index: 164414 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.3619. Min Act: -0.1700

Data Index: 722582 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.3305. Min Act: -0.1700

Data Index: 442502 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.2677. Min Act: -0.1700

Data Index: 1193481 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.2677. Min Act: -0.1700

Data Index: 473648 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.2205. Min Act: -0.1700

Data Index: 1015654 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.2363. Min Act: -0.1700

Data Index: 981053 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.2363. Min Act: -0.1700

Data Index: 784255 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.2205. Min Act: -0.1700

Data Index: 1202517 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.1733. Min Act: -0.1700

Data Index: 396999 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.1733. Min Act: -0.1700

Data Index: 1218521 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.1891. Min Act: -0.1700

Data Index: 1137212 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.2048. Min Act: -0.1700

Data Index: 35119 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.1576. Min Act: -0.1700

Data Index: 449413 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.1418. Min Act: -0.1700

Data Index: 1085167 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.1576. Min Act: -0.1700

Data Index: 855807 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.1261. Min Act: -0.1700

Data Index: 494774 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 3.4247. Min Range: -3.4247

Max Act: 3.1418. Min Act: -0.1700

Data Index: 539566 (C4 (Web Text))

Max Activating Token Index: 202