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

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

Neuron 1367 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: 0.1552. Min Range: -0.1552

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1317307 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1268809 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1376. Min Act: 0.0000

Data Index: 523375 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1287. Min Act: -0.0001

Data Index: 859209 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1207. Min Act: -0.0001

Data Index: 579631 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1286. Min Act: -0.0000

Data Index: 30181 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1138335 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1219. Min Act: -0.0001

Data Index: 39980 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1166. Min Act: -0.0001

Data Index: 860172 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1101. Min Act: 0.0001

Data Index: 388246 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1093. Min Act: 0.0000

Data Index: 1101760 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1127. Min Act: -0.0001

Data Index: 509727 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1285049 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1216786 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1095. Min Act: -0.0000

Data Index: 377871 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1192. Min Act: -0.0001

Data Index: 847545 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1070. Min Act: -0.0001

Data Index: 103213 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1106. Min Act: -0.0001

Data Index: 947974 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1281254 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.0993. Min Act: -0.0001

Data Index: 616407 (C4 (Web Text))

Max Activating Token Index: 744