Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 266 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.8187. Min Act: -0.1700

Data Index: 125185 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.8187. Min Act: -0.1700

Data Index: 1148088 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.7561. Min Act: -0.1700

Data Index: 1177803 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.7874. Min Act: -0.1700

Data Index: 1169136 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.8187. Min Act: -0.1700

Data Index: 1349697 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6936. Min Act: -0.1700

Data Index: 739230 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6936. Min Act: -0.1700

Data Index: 750816 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.7561. Min Act: -0.1700

Data Index: 1306193 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.7249. Min Act: -0.1700

Data Index: 413587 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.7561. Min Act: -0.1700

Data Index: 146109 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6936. Min Act: -0.1700

Data Index: 301360 (C4 (Web Text))

Max Activating Token Index: 759

Text #11

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6623. Min Act: -0.1700

Data Index: 914128 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6936. Min Act: -0.1700

Data Index: 38437 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6623. Min Act: -0.1700

Data Index: 926447 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.7249. Min Act: -0.1700

Data Index: 1333234 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6936. Min Act: -0.1700

Data Index: 466582 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6623. Min Act: -0.1700

Data Index: 1151854 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6936. Min Act: -0.1700

Data Index: 410275 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6310. Min Act: -0.1700

Data Index: 165882 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 3.8187. Min Range: -3.8187

Max Act: 3.6936. Min Act: -0.1700

Data Index: 996950 (C4 (Web Text))

Max Activating Token Index: 593