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

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

Neuron 1259 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: 3.6232. Min Range: -3.6232

Max Act: 3.6148. Min Act: -0.1700

Data Index: 256875 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.6195. Min Act: -0.1700

Data Index: 257442 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.6232. Min Act: -0.1700

Data Index: 426163 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5805. Min Act: -0.1700

Data Index: 1231549 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5896. Min Act: -0.1700

Data Index: 953741 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5376. Min Act: -0.1700

Data Index: 377916 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5522. Min Act: -0.1700

Data Index: 524158 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5484. Min Act: -0.1700

Data Index: 61863 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5620. Min Act: -0.1700

Data Index: 1211048 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5607. Min Act: -0.1700

Data Index: 134550 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5078. Min Act: -0.1700

Data Index: 1074653 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5394. Min Act: -0.1700

Data Index: 1071813 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5177. Min Act: -0.1700

Data Index: 819603 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5081. Min Act: -0.1700

Data Index: 1128279 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.5055. Min Act: -0.1700

Data Index: 85119 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.4773. Min Act: -0.1700

Data Index: 305340 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.4953. Min Act: -0.1700

Data Index: 830060 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.4965. Min Act: -0.1700

Data Index: 232646 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.4721. Min Act: -0.1700

Data Index: 526621 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 3.6232. Min Range: -3.6232

Max Act: 3.4837. Min Act: -0.1700

Data Index: 934290 (C4 (Web Text))

Max Activating Token Index: 435