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

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

Neuron 3176 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.9463. Min Act: 0.0001

Data Index: 1305224 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.6983. Min Act: -0.0000

Data Index: 388066 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.6493. Min Act: 0.0000

Data Index: 740658 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.5136. Min Act: 0.0000

Data Index: 1396747 (Python Code)

Max Activating Token Index: 410

Text #4

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.5999. Min Act: -0.0000

Data Index: 1532006 (Python Code)

Max Activating Token Index: 705

Text #5

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.4829. Min Act: 0.0001

Data Index: 1068576 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.5958. Min Act: -0.0000

Data Index: 1488838 (Python Code)

Max Activating Token Index: 906

Text #7

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.4270. Min Act: 0.0000

Data Index: 976921 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.5256. Min Act: -0.0000

Data Index: 1629397 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.6176. Min Act: -0.0000

Data Index: 529174 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.4811. Min Act: 0.0001

Data Index: 334757 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.4389. Min Act: 0.0000

Data Index: 445928 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.3942. Min Act: -0.0000

Data Index: 531156 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.3865. Min Act: 0.0000

Data Index: 924209 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.3280. Min Act: -0.0000

Data Index: 1569575 (Python Code)

Max Activating Token Index: 423

Text #15

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.3623. Min Act: -0.0000

Data Index: 970247 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1163669 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.2649. Min Act: 0.0000

Data Index: 470273 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.4389. Min Act: -0.0000

Data Index: 1071969 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.9463. Min Range: -1.9463

Max Act: 1.3073. Min Act: 0.0001

Data Index: 832324 (C4 (Web Text))

Max Activating Token Index: 114