Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1671 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.8206. Min Act: -0.1700

Data Index: 298130 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.7893. Min Act: -0.1700

Data Index: 565869 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.6642. Min Act: -0.1700

Data Index: 149033 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.6642. Min Act: -0.1700

Data Index: 124579 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.6015. Min Act: -0.1700

Data Index: 118663 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.6329. Min Act: -0.1700

Data Index: 71552 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.6015. Min Act: -0.1700

Data Index: 879474 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.6015. Min Act: -0.1700

Data Index: 783426 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.6015. Min Act: -0.1700

Data Index: 476434 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.6015. Min Act: -0.1700

Data Index: 141091 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.6015. Min Act: -0.1700

Data Index: 915565 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.5702. Min Act: -0.1700

Data Index: 776028 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.5702. Min Act: -0.1700

Data Index: 654293 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.4762. Min Act: -0.1700

Data Index: 837071 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.5702. Min Act: -0.1700

Data Index: 100192 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.5702. Min Act: -0.1700

Data Index: 52261 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.4762. Min Act: -0.1700

Data Index: 609385 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.5702. Min Act: -0.1700

Data Index: 392854 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.5702. Min Act: -0.1700

Data Index: 601892 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 3.8206. Min Range: -3.8206

Max Act: 3.5702. Min Act: -0.1700

Data Index: 231102 (C4 (Web Text))

Max Activating Token Index: 242