Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1293 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.4388. Min Act: -0.0001

Data Index: 754391 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3980. Min Act: -0.0001

Data Index: 691353 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3976. Min Act: -0.0001

Data Index: 16984 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3604. Min Act: -0.0001

Data Index: 1173294 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.4157. Min Act: -0.0001

Data Index: 1325924 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3682. Min Act: -0.0001

Data Index: 630717 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3561. Min Act: -0.0001

Data Index: 871182 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3562. Min Act: -0.0001

Data Index: 506229 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3378. Min Act: -0.0001

Data Index: 626179 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3596. Min Act: -0.0001

Data Index: 877025 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3539. Min Act: -0.0001

Data Index: 933398 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3644. Min Act: -0.0001

Data Index: 47373 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3407. Min Act: -0.0001

Data Index: 532739 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3396. Min Act: -0.0001

Data Index: 1028540 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1290001 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3064. Min Act: -0.0001

Data Index: 1271393 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2815. Min Act: -0.0001

Data Index: 665862 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1334359 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2911. Min Act: -0.0001

Data Index: 98062 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.4388. Min Range: -0.4388

Max Act: 0.2820. Min Act: -0.0001

Data Index: 174592 (C4 (Web Text))

Max Activating Token Index: 537