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

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

Neuron 1506 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: 3.9366. Min Range: -3.9366

Max Act: 3.9366. Min Act: -0.0000

Data Index: 251426 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 3.9366. Min Range: -3.9366

Max Act: 3.7158. Min Act: -0.0000

Data Index: 855251 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 3.9366. Min Range: -3.9366

Max Act: 3.3514. Min Act: -0.0000

Data Index: 402787 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 3.9366. Min Range: -3.9366

Max Act: 3.1915. Min Act: -0.0000

Data Index: 538991 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 3.9366. Min Range: -3.9366

Max Act: 3.1934. Min Act: -0.0000

Data Index: 1234055 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.9641. Min Act: -0.0000

Data Index: 346190 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 3.9366. Min Range: -3.9366

Max Act: 3.0732. Min Act: -0.0000

Data Index: 1256104 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.9034. Min Act: -0.0000

Data Index: 847452 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 3.9366. Min Range: -3.9366

Max Act: 3.0053. Min Act: -0.0000

Data Index: 1225743 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.8539. Min Act: -0.0000

Data Index: 1127713 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 3.9366. Min Range: -3.9366

Max Act: 3.1224. Min Act: -0.0000

Data Index: 142823 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.9591. Min Act: -0.0000

Data Index: 1122335 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.9638. Min Act: -0.0000

Data Index: 36501 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.8162. Min Act: -0.0000

Data Index: 816311 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.7905. Min Act: -0.0000

Data Index: 1276588 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.8138. Min Act: -0.0000

Data Index: 946769 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.9414. Min Act: -0.0000

Data Index: 624977 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.9239. Min Act: -0.0000

Data Index: 683227 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.9206. Min Act: -0.0000

Data Index: 1318423 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 3.9366. Min Range: -3.9366

Max Act: 2.4709. Min Act: -0.0000

Data Index: 1227495 (C4 (Web Text))

Max Activating Token Index: 817