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

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

Neuron 4900 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: 0.5107. Min Range: -0.5107

Max Act: 0.5107. Min Act: 0.0000

Data Index: 1413878 (Python Code)

Max Activating Token Index: 764

Text #1

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.4400. Min Act: -0.0000

Data Index: 946819 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3970. Min Act: -0.0000

Data Index: 578828 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1345128 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1479167 (Python Code)

Max Activating Token Index: 934

Text #5

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3532. Min Act: -0.0000

Data Index: 401213 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3339. Min Act: -0.0000

Data Index: 438260 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1595190 (Python Code)

Max Activating Token Index: 745

Text #8

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1214875 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3245. Min Act: -0.0000

Data Index: 486300 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3320. Min Act: -0.0000

Data Index: 744338 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1093134 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1620371 (Python Code)

Max Activating Token Index: 399

Text #13

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3105. Min Act: 0.0000

Data Index: 1458308 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1208338 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1208554 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1234387 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1316612 (C4 (Web Text))

Max Activating Token Index: 856

Text #18

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.2986. Min Act: -0.0000

Data Index: 583799 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.5107. Min Range: -0.5107

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1091769 (C4 (Web Text))

Max Activating Token Index: 791