Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2273 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1786. Min Range: -4.1786

Max Act: 4.1786. Min Act: -0.0001

Data Index: 352853 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 4.1786. Min Range: -4.1786

Max Act: 4.1340. Min Act: -0.0001

Data Index: 526291 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 4.1786. Min Range: -4.1786

Max Act: 4.0520. Min Act: -0.0001

Data Index: 145458 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 4.1786. Min Range: -4.1786

Max Act: 3.2457. Min Act: -0.0001

Data Index: 80445 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.8636. Min Act: -0.0001

Data Index: 244271 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.6383. Min Act: -0.0001

Data Index: 1062444 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.6125. Min Act: -0.0001

Data Index: 493301 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.5917. Min Act: -0.0001

Data Index: 654969 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.4915. Min Act: -0.0001

Data Index: 64533 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.6110. Min Act: -0.0001

Data Index: 89860 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.5632. Min Act: -0.0001

Data Index: 803299 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.5125. Min Act: -0.0001

Data Index: 55844 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.5209. Min Act: -0.0001

Data Index: 287019 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.3524. Min Act: -0.0001

Data Index: 52240 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.3481. Min Act: -0.0001

Data Index: 951194 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.3172. Min Act: -0.0001

Data Index: 630473 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.4020. Min Act: -0.0001

Data Index: 1228726 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.1569. Min Act: -0.0001

Data Index: 840719 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.3624. Min Act: -0.0001

Data Index: 754168 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 4.1786. Min Range: -4.1786

Max Act: 2.5847. Min Act: -0.0001

Data Index: 1217094 (C4 (Web Text))

Max Activating Token Index: 926