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

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

Neuron 2460 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: 3.9692. Min Range: -3.9692

Max Act: 3.7412. Min Act: -0.0000

Data Index: 1264627 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.9035. Min Act: -0.0000

Data Index: 401536 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8310. Min Act: -0.0000

Data Index: 383754 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.5243. Min Act: -0.0000

Data Index: 1076052 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.5181. Min Act: -0.0001

Data Index: 97565 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.9692. Min Act: -0.0001

Data Index: 753378 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.6400. Min Act: -0.0001

Data Index: 1339996 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.6992. Min Act: -0.0000

Data Index: 1078325 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3977. Min Act: -0.0001

Data Index: 1198885 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.5258. Min Act: -0.0000

Data Index: 948991 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.4742. Min Act: -0.0001

Data Index: 334857 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.4939. Min Act: -0.0000

Data Index: 368000 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3922. Min Act: -0.0000

Data Index: 773804 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.2408. Min Act: -0.0001

Data Index: 333804 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3411. Min Act: -0.0000

Data Index: 1018811 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.1967. Min Act: -0.0000

Data Index: 871833 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3351. Min Act: -0.0000

Data Index: 251939 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.3054. Min Act: -0.0001

Data Index: 358897 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.2988. Min Act: -0.0001

Data Index: 491713 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.6104. Min Act: -0.0001

Data Index: 1281974 (C4 (Web Text))

Max Activating Token Index: 284