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

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

Neuron 4331 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3896. Min Range: -5.3896

Max Act: 5.3896. Min Act: -0.0001

Data Index: 218971 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.5402. Min Act: -0.0001

Data Index: 79715 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.8251. Min Act: -0.0001

Data Index: 324610 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.4137. Min Act: -0.0001

Data Index: 131908 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.5309. Min Act: -0.0001

Data Index: 991557 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.1967. Min Act: -0.0001

Data Index: 752140 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.3440. Min Act: -0.0001

Data Index: 1282314 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.1139. Min Act: -0.0001

Data Index: 903648 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.2442. Min Act: -0.0001

Data Index: 897394 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.2444. Min Act: -0.0001

Data Index: 1184418 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 5.3896. Min Range: -5.3896

Max Act: 3.8652. Min Act: -0.0001

Data Index: 294306 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.2688. Min Act: -0.0001

Data Index: 414144 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 5.3896. Min Range: -5.3896

Max Act: 3.1706. Min Act: -0.0001

Data Index: 948316 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.1939. Min Act: -0.0001

Data Index: 895046 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.0344. Min Act: -0.0001

Data Index: 71857 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 5.3896. Min Range: -5.3896

Max Act: 3.7439. Min Act: -0.0001

Data Index: 1127879 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.2091. Min Act: -0.0001

Data Index: 499807 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 5.3896. Min Range: -5.3896

Max Act: 3.8308. Min Act: -0.0001

Data Index: 1257588 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.0218. Min Act: -0.0001

Data Index: 17229 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 5.3896. Min Range: -5.3896

Max Act: 4.0575. Min Act: -0.0001

Data Index: 23191 (C4 (Web Text))

Max Activating Token Index: 268