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

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

Neuron 168 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.5413. Min Act: -0.1700

Data Index: 563640 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.3851. Min Act: -0.1700

Data Index: 1274037 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.3538. Min Act: -0.1700

Data Index: 986568 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.3226. Min Act: -0.1700

Data Index: 236300 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.3382. Min Act: -0.1700

Data Index: 960449 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.3069. Min Act: -0.1700

Data Index: 1349757 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.2757. Min Act: -0.1700

Data Index: 415971 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.2601. Min Act: -0.1700

Data Index: 750838 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.3382. Min Act: -0.1700

Data Index: 747968 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.1976. Min Act: -0.1700

Data Index: 441634 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.2132. Min Act: -0.1700

Data Index: 1276753 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.1976. Min Act: -0.1700

Data Index: 509352 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.1507. Min Act: -0.1700

Data Index: 448012 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.1350. Min Act: -0.1700

Data Index: 803292 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.1663. Min Act: -0.1700

Data Index: 205416 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.1194. Min Act: -0.1700

Data Index: 602162 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.1038. Min Act: -0.1700

Data Index: 585694 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.0881. Min Act: -0.1700

Data Index: 1227341 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.0725. Min Act: -0.1700

Data Index: 234972 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 4.5413. Min Range: -4.5413

Max Act: 4.0569. Min Act: -0.1700

Data Index: 1134347 (C4 (Web Text))

Max Activating Token Index: 543