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

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

Neuron 679 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.4949. Min Act: -0.1700

Data Index: 757637 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.3699. Min Act: -0.1700

Data Index: 486736 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.4011. Min Act: -0.1700

Data Index: 13887 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.3699. Min Act: -0.1700

Data Index: 373949 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.4011. Min Act: -0.1700

Data Index: 614923 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.3699. Min Act: -0.1700

Data Index: 1146206 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.3074. Min Act: -0.1700

Data Index: 229483 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.3074. Min Act: -0.1700

Data Index: 571194 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.3074. Min Act: -0.1700

Data Index: 121962 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.3074. Min Act: -0.1700

Data Index: 462855 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.2449. Min Act: -0.1700

Data Index: 497591 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.3074. Min Act: -0.1700

Data Index: 1278986 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.2761. Min Act: -0.1700

Data Index: 352225 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.3074. Min Act: -0.1700

Data Index: 816621 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.2761. Min Act: -0.1700

Data Index: 495928 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.2761. Min Act: -0.1700

Data Index: 273984 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.2761. Min Act: -0.1699

Data Index: 206961 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.2761. Min Act: -0.1700

Data Index: 183613 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.3074. Min Act: -0.1700

Data Index: 957854 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 5.4949. Min Range: -5.4949

Max Act: 5.2136. Min Act: -0.1700

Data Index: 423777 (C4 (Web Text))

Max Activating Token Index: 319