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

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

Neuron 1928 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: 3.8238. Min Range: -3.8238

Max Act: 3.8238. Min Act: -0.1700

Data Index: 555791 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.7671. Min Act: -0.1700

Data Index: 1023551 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.7359. Min Act: -0.1700

Data Index: 700184 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.6531. Min Act: -0.1700

Data Index: 232103 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.6442. Min Act: -0.1700

Data Index: 1232854 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.6433. Min Act: -0.1700

Data Index: 484178 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.6459. Min Act: -0.1700

Data Index: 867612 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.6317. Min Act: -0.1700

Data Index: 940692 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.6083. Min Act: -0.1700

Data Index: 1315248 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.6020. Min Act: -0.1700

Data Index: 1291890 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.5779. Min Act: -0.1700

Data Index: 478381 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.5692. Min Act: -0.1700

Data Index: 169240 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.5849. Min Act: -0.1700

Data Index: 641053 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.5793. Min Act: -0.1700

Data Index: 1339146 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.5721. Min Act: -0.1700

Data Index: 1262039 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.5574. Min Act: -0.1700

Data Index: 292420 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.5308. Min Act: -0.1700

Data Index: 135389 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.5325. Min Act: -0.1700

Data Index: 429881 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.5265. Min Act: -0.1700

Data Index: 957010 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 3.8238. Min Range: -3.8238

Max Act: 3.5353. Min Act: -0.1700

Data Index: 195364 (C4 (Web Text))

Max Activating Token Index: 957