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

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

Neuron 2812 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1425495 (Python Code)

Max Activating Token Index: 338

Text #1

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1517342 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7221. Min Act: -0.0000

Data Index: 294686 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7046. Min Act: -0.0000

Data Index: 80890 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1284835 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1414344 (Python Code)

Max Activating Token Index: 899

Text #6

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1496270 (Python Code)

Max Activating Token Index: 837

Text #7

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6860. Min Act: -0.0000

Data Index: 214765 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6679. Min Act: -0.0000

Data Index: 1113396 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6820. Min Act: -0.0000

Data Index: 70540 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6454. Min Act: -0.0000

Data Index: 876875 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1607032 (Python Code)

Max Activating Token Index: 511

Text #12

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6717. Min Act: -0.0000

Data Index: 83043 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6476. Min Act: -0.0000

Data Index: 204166 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6516. Min Act: -0.0000

Data Index: 686381 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1051733 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1435621 (Python Code)

Max Activating Token Index: 346

Text #17

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6156. Min Act: -0.0000

Data Index: 192957 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1105587 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6169. Min Act: -0.0000

Data Index: 226256 (C4 (Web Text))

Max Activating Token Index: 38