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

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

Neuron 1481 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: 3.9461. Min Range: -3.9461

Max Act: 3.9396. Min Act: -0.1700

Data Index: 1018525 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.9257. Min Act: -0.1700

Data Index: 424571 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.9461. Min Act: -0.1700

Data Index: 1305186 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.8838. Min Act: -0.1700

Data Index: 1330828 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.8656. Min Act: -0.1700

Data Index: 887877 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.8341. Min Act: -0.1700

Data Index: 201962 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.8375. Min Act: -0.1700

Data Index: 394431 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.8385. Min Act: -0.1700

Data Index: 462055 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.8225. Min Act: -0.1700

Data Index: 888997 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.7959. Min Act: -0.1700

Data Index: 1146555 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.8179. Min Act: -0.1700

Data Index: 1241111 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.7860. Min Act: -0.1700

Data Index: 23091 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.8103. Min Act: -0.1700

Data Index: 679206 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.7842. Min Act: -0.1700

Data Index: 349472 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.7815. Min Act: -0.1700

Data Index: 214316 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.7867. Min Act: -0.1700

Data Index: 879220 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.7902. Min Act: -0.1700

Data Index: 1062134 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.7547. Min Act: -0.1700

Data Index: 1112322 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.7423. Min Act: -0.1700

Data Index: 1083566 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 3.9461. Min Range: -3.9461

Max Act: 3.7494. Min Act: -0.1700

Data Index: 594938 (C4 (Web Text))

Max Activating Token Index: 822