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

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

Neuron 4919 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1361175 (Python Code)

Max Activating Token Index: 542

Text #1

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.5967. Min Act: -0.0000

Data Index: 44168 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.5486. Min Act: -0.0000

Data Index: 761167 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4613. Min Act: -0.0000

Data Index: 895739 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1406823 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4828. Min Act: -0.0000

Data Index: 392450 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4332. Min Act: -0.0000

Data Index: 130701 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4014. Min Act: -0.0000

Data Index: 293196 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1347226 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1387207 (Python Code)

Max Activating Token Index: 394

Text #10

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1568081 (Python Code)

Max Activating Token Index: 933

Text #11

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4368. Min Act: -0.0000

Data Index: 219062 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4240. Min Act: -0.0000

Data Index: 668570 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4470. Min Act: -0.0000

Data Index: 280502 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1112436 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1275554 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4054. Min Act: -0.0000

Data Index: 148961 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1147509 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1526632 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 0.6183. Min Range: -0.6183

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1402422 (Python Code)

Max Activating Token Index: 387