Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 979 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.3387. Min Act: -0.0001
Data Index: 773738 (C4 (Web Text))
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2849. Min Act: -0.0001
Data Index: 1608100 (Python Code)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2882. Min Act: -0.0001
Data Index: 448669 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.2099. Min Act: -0.0001
Data Index: 501744 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.0462. Min Act: -0.0001
Data Index: 1379648 (Python Code)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.0529. Min Act: -0.0001
Data Index: 694031 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.0769. Min Act: -0.0001
Data Index: 424033 (C4 (Web Text))
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.0410. Min Act: -0.0001
Data Index: 437604 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.0828. Min Act: -0.0001
Data Index: 470214 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.1342. Min Act: -0.0001
Data Index: 1032363 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.0972. Min Act: -0.0001
Data Index: 92369 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.1563. Min Act: -0.0001
Data Index: 1052220 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.0917. Min Act: -0.0001
Data Index: 915555 (C4 (Web Text))
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.0208. Min Act: -0.0001
Data Index: 322481 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3387. Min Range: -1.3387
Max Act: 0.9196. Min Act: -0.0001
Data Index: 1186385 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.0370. Min Act: -0.0001
Data Index: 611610 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.0257. Min Act: -0.0001
Data Index: 412245 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.0708. Min Act: -0.0001
Data Index: 735225 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3387. Min Range: -1.3387
Max Act: 0.9808. Min Act: -0.0001
Data Index: 845488 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3387. Min Range: -1.3387
Max Act: 1.1451. Min Act: -0.0001
Data Index: 1497580 (Python Code)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19