Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1620 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.7532. Min Act: -0.1700

Data Index: 364543 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.5657. Min Act: -0.1700

Data Index: 797343 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.5344. Min Act: -0.1700

Data Index: 194490 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.5032. Min Act: -0.1700

Data Index: 26925 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.5657. Min Act: -0.1700

Data Index: 812271 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.6282. Min Act: -0.1700

Data Index: 859109 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.4407. Min Act: -0.1700

Data Index: 988560 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.3782. Min Act: -0.1700

Data Index: 651896 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.3782. Min Act: -0.1700

Data Index: 683796 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.4407. Min Act: -0.1700

Data Index: 243256 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.3157. Min Act: -0.1700

Data Index: 195602 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.3469. Min Act: -0.1700

Data Index: 324197 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.3469. Min Act: -0.1700

Data Index: 719967 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.3782. Min Act: -0.1700

Data Index: 226440 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.2844. Min Act: -0.1700

Data Index: 1176425 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.3469. Min Act: -0.1700

Data Index: 270040 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.3157. Min Act: -0.1700

Data Index: 1226572 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.3157. Min Act: -0.1700

Data Index: 1229259 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.3469. Min Act: -0.1700

Data Index: 670276 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 5.7532. Min Range: -5.7532

Max Act: 5.3157. Min Act: -0.1700

Data Index: 478278 (C4 (Web Text))

Max Activating Token Index: 237