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

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

Neuron 1706 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: 3.6731. Min Range: -3.6731

Max Act: 3.6731. Min Act: -0.1700

Data Index: 1052253 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.6435. Min Act: -0.1700

Data Index: 1010091 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.6331. Min Act: -0.1700

Data Index: 828145 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5952. Min Act: -0.1700

Data Index: 675298 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5617. Min Act: -0.1700

Data Index: 514801 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5451. Min Act: -0.1700

Data Index: 1307490 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5659. Min Act: -0.1700

Data Index: 196273 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5460. Min Act: -0.1700

Data Index: 843272 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5292. Min Act: -0.1700

Data Index: 500604 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5211. Min Act: -0.1700

Data Index: 1309312 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5318. Min Act: -0.1700

Data Index: 1019756 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5237. Min Act: -0.1700

Data Index: 404379 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5318. Min Act: -0.1700

Data Index: 179456 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5370. Min Act: -0.1700

Data Index: 258184 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5365. Min Act: -0.1700

Data Index: 1249052 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5279. Min Act: -0.1700

Data Index: 264124 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5006. Min Act: -0.1700

Data Index: 806996 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5065. Min Act: -0.1700

Data Index: 162433 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.4723. Min Act: -0.1700

Data Index: 1586444 (Python Code)

Max Activating Token Index: 270

Text #19

Max Range: 3.6731. Min Range: -3.6731

Max Act: 3.5010. Min Act: -0.1700

Data Index: 784201 (C4 (Web Text))

Max Activating Token Index: 999