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

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

Neuron 2951 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3831. Min Act: -0.0001

Data Index: 1482032 (Python Code)

Max Activating Token Index: 492

Text #1

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.4039. Min Act: -0.0001

Data Index: 1229536 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3839. Min Act: -0.0001

Data Index: 1458931 (Python Code)

Max Activating Token Index: 926

Text #3

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3741. Min Act: -0.0001

Data Index: 1271139 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3663. Min Act: -0.0001

Data Index: 1524746 (Python Code)

Max Activating Token Index: 916

Text #5

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3674. Min Act: -0.0001

Data Index: 391787 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3643. Min Act: -0.0001

Data Index: 669259 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3419. Min Act: -0.0001

Data Index: 511373 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3308. Min Act: -0.0001

Data Index: 1611519 (Python Code)

Max Activating Token Index: 486

Text #9

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3345. Min Act: -0.0001

Data Index: 1509838 (Python Code)

Max Activating Token Index: 886

Text #10

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3240. Min Act: -0.0001

Data Index: 889030 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3381. Min Act: -0.0001

Data Index: 743301 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3401. Min Act: -0.0001

Data Index: 1266264 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.2903. Min Act: -0.0001

Data Index: 1224980 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3228. Min Act: -0.0001

Data Index: 1653914 (Python Code)

Max Activating Token Index: 851

Text #15

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3103. Min Act: -0.0001

Data Index: 43181 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3200. Min Act: -0.0001

Data Index: 1542162 (Python Code)

Max Activating Token Index: 905

Text #17

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3200. Min Act: -0.0001

Data Index: 422589 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3203. Min Act: -0.0001

Data Index: 740243 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.4039. Min Range: -0.4039

Max Act: 0.3050. Min Act: -0.0001

Data Index: 718314 (C4 (Web Text))

Max Activating Token Index: 222