Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3138 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1668. Min Act: -0.0001

Data Index: 184813 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1336. Min Act: -0.0001

Data Index: 836429 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1383. Min Act: -0.0001

Data Index: 820239 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1217. Min Act: -0.0001

Data Index: 628160 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1224. Min Act: -0.0001

Data Index: 972950 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1205. Min Act: -0.0001

Data Index: 141087 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1230. Min Act: -0.0000

Data Index: 798033 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1170. Min Act: -0.0000

Data Index: 914155 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1299666 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1070. Min Act: -0.0001

Data Index: 550743 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1178. Min Act: -0.0000

Data Index: 481408 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1075. Min Act: -0.0001

Data Index: 202402 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1115. Min Act: -0.0000

Data Index: 840129 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1108. Min Act: -0.0000

Data Index: 505639 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1060. Min Act: -0.0001

Data Index: 993062 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1147893 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1050. Min Act: -0.0000

Data Index: 713883 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1128467 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1082. Min Act: -0.0000

Data Index: 502950 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.1668. Min Range: -0.1668

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1239290 (C4 (Web Text))

Max Activating Token Index: 60