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

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

Neuron 718 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1671. Min Act: -0.0000

Data Index: 625992 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1431929 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1484556 (Python Code)

Max Activating Token Index: 395

Text #3

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1148352 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1242. Min Act: -0.0000

Data Index: 618770 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1582866 (Python Code)

Max Activating Token Index: 545

Text #6

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1207. Min Act: -0.0001

Data Index: 411269 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1653935 (Python Code)

Max Activating Token Index: 234

Text #8

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1311612 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1537471 (Python Code)

Max Activating Token Index: 214

Text #10

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1586984 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1435249 (Python Code)

Max Activating Token Index: 1006

Text #12

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1628222 (Python Code)

Max Activating Token Index: 595

Text #13

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1106. Min Act: -0.0001

Data Index: 116977 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1389616 (Python Code)

Max Activating Token Index: 188

Text #15

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1631736 (Python Code)

Max Activating Token Index: 616

Text #16

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1511686 (Python Code)

Max Activating Token Index: 417

Text #17

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1297296 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1099. Min Act: -0.0001

Data Index: 602224 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.1671. Min Range: -0.1671

Max Act: 0.1040. Min Act: -0.0001

Data Index: 525242 (C4 (Web Text))

Max Activating Token Index: 217