Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1358 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.4457. Min Range: -1.4457
Max Act: 0.9734. Min Act: -0.0001
Data Index: 926369 (The Pile)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4457. Min Range: -1.4457
Max Act: 1.1410. Min Act: -0.0001
Data Index: 990807 (The Pile)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4457. Min Range: -1.4457
Max Act: 1.4457. Min Act: -0.0001
Data Index: 763818 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4457. Min Range: -1.4457
Max Act: 1.0507. Min Act: -0.0001
Data Index: 794101 (The Pile)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4457. Min Range: -1.4457
Max Act: 1.1435. Min Act: -0.0001
Data Index: 754296 (The Pile)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4457. Min Range: -1.4457
Max Act: 1.1154. Min Act: -0.0001
Data Index: 165506 (The Pile)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4457. Min Range: -1.4457
Max Act: 1.0210. Min Act: -0.0001
Data Index: 235036 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4457. Min Range: -1.4457
Max Act: 1.1064. Min Act: -0.0001
Data Index: 110839 (The Pile)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4457. Min Range: -1.4457
Max Act: 1.1009. Min Act: -0.0001
Data Index: 355452 (The Pile)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4457. Min Range: -1.4457
Max Act: 1.2702. Min Act: -0.0001
Data Index: 917534 (The Pile)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4457. Min Range: -1.4457
Max Act: 1.0230. Min Act: -0.0001
Data Index: 777831 (The Pile)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4457. Min Range: -1.4457
Max Act: 0.6081. Min Act: -0.0001
Data Index: 1239412 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4457. Min Range: -1.4457
Max Act: 0.8199. Min Act: -0.0001
Data Index: 948713 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4457. Min Range: -1.4457
Max Act: 0.9391. Min Act: -0.0001
Data Index: 860274 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4457. Min Range: -1.4457
Max Act: 0.9322. Min Act: -0.0001
Data Index: 1809972 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4457. Min Range: -1.4457
Max Act: 0.7848. Min Act: -0.0001
Data Index: 1794945 (The Pile)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4457. Min Range: -1.4457
Max Act: 0.9904. Min Act: -0.0001
Data Index: 739401 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4457. Min Range: -1.4457
Max Act: 0.8837. Min Act: -0.0001
Data Index: 667937 (The Pile)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4457. Min Range: -1.4457
Max Act: 1.0625. Min Act: -0.0001
Data Index: 490392 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4457. Min Range: -1.4457
Max Act: 0.9732. Min Act: -0.0001
Data Index: 1250093 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19