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

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

Neuron 521 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: 3.1749. Min Range: -3.1749

Max Act: 3.1749. Min Act: -0.1700

Data Index: 697120 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.1244. Min Act: -0.1700

Data Index: 538718 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.1344. Min Act: -0.1700

Data Index: 516437 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0949. Min Act: -0.1700

Data Index: 1276497 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0927. Min Act: -0.1700

Data Index: 391221 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0693. Min Act: -0.1700

Data Index: 931254 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0654. Min Act: -0.1700

Data Index: 788889 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0663. Min Act: -0.1700

Data Index: 500274 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0618. Min Act: -0.1700

Data Index: 554381 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0374. Min Act: -0.1700

Data Index: 609135 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0407. Min Act: -0.1700

Data Index: 203780 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0433. Min Act: -0.1700

Data Index: 1487099 (Python Code)

Max Activating Token Index: 239

Text #12

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0424. Min Act: -0.1700

Data Index: 1056120 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0260. Min Act: -0.1700

Data Index: 813128 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0263. Min Act: -0.1700

Data Index: 395901 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0393. Min Act: -0.1700

Data Index: 1320016 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0218. Min Act: -0.1700

Data Index: 280202 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0152. Min Act: -0.1700

Data Index: 1149040 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0135. Min Act: -0.1700

Data Index: 278740 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 3.1749. Min Range: -3.1749

Max Act: 3.0384. Min Act: -0.1700

Data Index: 1570660 (Python Code)

Max Activating Token Index: 500