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

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

Neuron 3166 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: 1.7324. Min Range: -1.7324

Max Act: 1.7324. Min Act: -0.0000

Data Index: 1307596 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.5627. Min Act: -0.0000

Data Index: 302300 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.5336. Min Act: -0.0000

Data Index: 930216 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.4233. Min Act: -0.0000

Data Index: 1171027 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.4675. Min Act: -0.0000

Data Index: 903423 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.4922. Min Act: -0.0000

Data Index: 295554 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.3107. Min Act: -0.0000

Data Index: 45586 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.3874. Min Act: -0.0000

Data Index: 421253 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.3484. Min Act: -0.0000

Data Index: 61772 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1291944 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.3396. Min Act: -0.0000

Data Index: 45855 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.3810. Min Act: -0.0000

Data Index: 541319 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.4190. Min Act: -0.0000

Data Index: 1548255 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.4090. Min Act: -0.0000

Data Index: 319368 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.3695. Min Act: -0.0000

Data Index: 980845 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.4454. Min Act: -0.0000

Data Index: 453649 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.3303. Min Act: -0.0000

Data Index: 206678 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.4026. Min Act: -0.0000

Data Index: 1113867 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.3341. Min Act: -0.0000

Data Index: 676611 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 1.7324. Min Range: -1.7324

Max Act: 1.3454. Min Act: -0.0000

Data Index: 1502760 (Python Code)

Max Activating Token Index: 41