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

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

Neuron 18 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: 4.1248. Min Range: -4.1248

Max Act: 4.1248. Min Act: -0.1700

Data Index: 493447 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 4.1248. Min Range: -4.1248

Max Act: 4.1007. Min Act: -0.1700

Data Index: 20035 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 4.1248. Min Range: -4.1248

Max Act: 4.0592. Min Act: -0.1700

Data Index: 1358685 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 4.1248. Min Range: -4.1248

Max Act: 4.0525. Min Act: -0.1700

Data Index: 1025553 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 4.1248. Min Range: -4.1248

Max Act: 4.0623. Min Act: -0.1700

Data Index: 156610 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 4.1248. Min Range: -4.1248

Max Act: 4.0386. Min Act: -0.1700

Data Index: 1146042 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 4.1248. Min Range: -4.1248

Max Act: 4.0324. Min Act: -0.1700

Data Index: 792144 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.9627. Min Act: -0.1700

Data Index: 1259825 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 4.1248. Min Range: -4.1248

Max Act: 4.0191. Min Act: -0.1700

Data Index: 417213 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.9695. Min Act: -0.1700

Data Index: 1033925 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.9340. Min Act: -0.1700

Data Index: 866123 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.9285. Min Act: -0.1700

Data Index: 1167812 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.9318. Min Act: -0.1700

Data Index: 47420 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.9084. Min Act: -0.1700

Data Index: 906074 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.9104. Min Act: -0.1700

Data Index: 427430 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.8991. Min Act: -0.1700

Data Index: 1132272 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.9249. Min Act: -0.1700

Data Index: 819998 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.9255. Min Act: -0.1700

Data Index: 368871 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.8880. Min Act: -0.1700

Data Index: 219663 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 4.1248. Min Range: -4.1248

Max Act: 3.8537. Min Act: -0.1700

Data Index: 234739 (C4 (Web Text))

Max Activating Token Index: 355