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

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

Neuron 2819 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: 4.8645. Min Range: -4.8645

Max Act: 4.8645. Min Act: -0.0000

Data Index: 583737 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 4.8645. Min Range: -4.8645

Max Act: 4.3345. Min Act: -0.0000

Data Index: 22467 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 4.8645. Min Range: -4.8645

Max Act: 4.4449. Min Act: -0.0000

Data Index: 700896 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 4.8645. Min Range: -4.8645

Max Act: 4.3058. Min Act: -0.0000

Data Index: 339981 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 4.8645. Min Range: -4.8645

Max Act: 4.2252. Min Act: -0.0000

Data Index: 242564 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.9152. Min Act: -0.0000

Data Index: 800231 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.8150. Min Act: -0.0000

Data Index: 1109214 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.9119. Min Act: -0.0000

Data Index: 1154512 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.8890. Min Act: -0.0000

Data Index: 52500 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.7287. Min Act: -0.0000

Data Index: 984518 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 4.8645. Min Range: -4.8645

Max Act: 4.1935. Min Act: -0.0000

Data Index: 581545 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.8268. Min Act: -0.0000

Data Index: 286148 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.9735. Min Act: -0.0000

Data Index: 244800 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.7428. Min Act: -0.0000

Data Index: 501089 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.1435. Min Act: -0.0000

Data Index: 887379 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.7540. Min Act: -0.0000

Data Index: 999728 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.8843. Min Act: -0.0000

Data Index: 951323 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.2445. Min Act: -0.0000

Data Index: 29391 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.6934. Min Act: -0.0000

Data Index: 1253208 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 4.8645. Min Range: -4.8645

Max Act: 3.5174. Min Act: -0.0000

Data Index: 399054 (C4 (Web Text))

Max Activating Token Index: 78