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

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

Neuron 1591 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: 3.3253. Min Range: -3.3253

Max Act: 3.3143. Min Act: -0.1700

Data Index: 301412 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.3253. Min Act: -0.1700

Data Index: 1227870 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.2916. Min Act: -0.1700

Data Index: 89207 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.2186. Min Act: -0.1700

Data Index: 696907 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1832. Min Act: -0.1700

Data Index: 1108245 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1982. Min Act: -0.1700

Data Index: 1134374 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1697. Min Act: -0.1700

Data Index: 85984 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1712. Min Act: -0.1697

Data Index: 191857 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1609. Min Act: -0.1700

Data Index: 1147232 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1786. Min Act: -0.1700

Data Index: 1450 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1567. Min Act: -0.1700

Data Index: 164487 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1459. Min Act: -0.1700

Data Index: 82645 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1622. Min Act: -0.1699

Data Index: 794874 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1423. Min Act: -0.1699

Data Index: 1072654 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1449. Min Act: -0.1700

Data Index: 372071 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1111. Min Act: -0.1700

Data Index: 706015 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1140. Min Act: -0.1700

Data Index: 856581 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1151. Min Act: -0.1700

Data Index: 356025 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1147. Min Act: -0.1700

Data Index: 165111 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 3.3253. Min Range: -3.3253

Max Act: 3.1187. Min Act: -0.1700

Data Index: 1165089 (C4 (Web Text))

Max Activating Token Index: 21