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

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

Neuron 1331 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0441. Min Range: -3.0441

Max Act: 3.0441. Min Act: -0.0000

Data Index: 1063107 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.7993. Min Act: -0.0000

Data Index: 490557 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.7506. Min Act: -0.0000

Data Index: 267388 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.6409. Min Act: -0.0000

Data Index: 1357320 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.7238. Min Act: -0.0000

Data Index: 296017 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.6135. Min Act: -0.0000

Data Index: 278957 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.3953. Min Act: -0.0000

Data Index: 620909 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.3218. Min Act: -0.0000

Data Index: 561093 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.5744. Min Act: -0.0000

Data Index: 1279477 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.3512. Min Act: -0.0000

Data Index: 803530 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.3400. Min Act: -0.0000

Data Index: 966880 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.4245. Min Act: -0.0000

Data Index: 59478 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.1658. Min Act: -0.0000

Data Index: 449 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.2729. Min Act: -0.0000

Data Index: 61095 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.2683. Min Act: -0.0000

Data Index: 1138201 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.3615. Min Act: -0.0000

Data Index: 1217382 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.3335. Min Act: -0.0000

Data Index: 1171191 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 3.0441. Min Range: -3.0441

Max Act: 1.9852. Min Act: -0.0000

Data Index: 1092232 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 3.0441. Min Range: -3.0441

Max Act: 1.9088. Min Act: -0.0000

Data Index: 1262128 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 3.0441. Min Range: -3.0441

Max Act: 2.0169. Min Act: -0.0000

Data Index: 900409 (C4 (Web Text))

Max Activating Token Index: 826