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

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

Neuron 158 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: 3.7185. Min Range: -3.7185

Max Act: 3.7185. Min Act: -0.1700

Data Index: 529440 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6892. Min Act: -0.1700

Data Index: 934283 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5976. Min Act: -0.1700

Data Index: 1165224 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5810. Min Act: -0.1700

Data Index: 542630 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5740. Min Act: -0.1700

Data Index: 1357380 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5572. Min Act: -0.1700

Data Index: 1270836 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5522. Min Act: -0.1700

Data Index: 72919 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5490. Min Act: -0.1700

Data Index: 60883 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5586. Min Act: -0.1700

Data Index: 985427 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5194. Min Act: -0.1700

Data Index: 670972 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5063. Min Act: -0.1700

Data Index: 708655 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5013. Min Act: -0.1700

Data Index: 259017 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5053. Min Act: -0.1700

Data Index: 1118656 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.4980. Min Act: -0.1700

Data Index: 961835 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.4909. Min Act: -0.1700

Data Index: 1258034 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.4702. Min Act: -0.1700

Data Index: 1289304 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.4777. Min Act: -0.1700

Data Index: 151750 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.4893. Min Act: -0.1700

Data Index: 7726 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.4785. Min Act: -0.1700

Data Index: 302411 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.4652. Min Act: -0.1700

Data Index: 542169 (C4 (Web Text))

Max Activating Token Index: 727