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

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

Neuron 2566 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1407. Min Act: -0.0001

Data Index: 895677 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1452. Min Act: -0.0001

Data Index: 954613 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1343. Min Act: -0.0001

Data Index: 580196 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1389. Min Act: -0.0001

Data Index: 260806 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1195. Min Act: -0.0001

Data Index: 928800 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1147679 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1309. Min Act: -0.0000

Data Index: 540829 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1163. Min Act: -0.0001

Data Index: 565862 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1194. Min Act: -0.0001

Data Index: 652710 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1238. Min Act: -0.0001

Data Index: 839853 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1256. Min Act: -0.0001

Data Index: 944290 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1184. Min Act: -0.0001

Data Index: 1065911 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1246. Min Act: -0.0001

Data Index: 853465 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1130. Min Act: -0.0001

Data Index: 310331 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1143. Min Act: -0.0001

Data Index: 848877 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1173. Min Act: 0.0000

Data Index: 1259781 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1137. Min Act: -0.0001

Data Index: 438883 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1078. Min Act: 0.0000

Data Index: 123507 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1125. Min Act: -0.0001

Data Index: 706782 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.1452. Min Range: -0.1452

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1267065 (C4 (Web Text))

Max Activating Token Index: 814