Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 39 in Layer 1
Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')
Click the toggle to see the full text!
Text #0
Max Range: 2.2012. Min Range: -2.2012
Max Act: 2.2012. Min Act: -0.0002
Data Index: 346675 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 2.2012. Min Range: -2.2012
Max Act: 2.0423. Min Act: -0.0002
Data Index: 641310 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 2.2012. Min Range: -2.2012
Max Act: 2.0188. Min Act: -0.0002
Data Index: 1239728 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 2.2012. Min Range: -2.2012
Max Act: 2.0353. Min Act: -0.0002
Data Index: 909652 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.9966. Min Act: -0.0002
Data Index: 582255 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.9437. Min Act: -0.0002
Data Index: 932915 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.9268. Min Act: -0.0002
Data Index: 608752 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.8961. Min Act: -0.0002
Data Index: 145113 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.8733. Min Act: -0.0002
Data Index: 889036 (C4 (Web Text))
Max Activating Token Index: 458
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.8884. Min Act: -0.0002
Data Index: 683758 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.8660. Min Act: -0.0002
Data Index: 694861 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.9105. Min Act: -0.0002
Data Index: 1017406 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.9364. Min Act: -0.0002
Data Index: 82512 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.8974. Min Act: -0.0002
Data Index: 21009 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.8195. Min Act: -0.0002
Data Index: 1015379 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.9070. Min Act: -0.0002
Data Index: 978976 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.8335. Min Act: -0.0002
Data Index: 1079500 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.8601. Min Act: -0.0002
Data Index: 682689 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.8616. Min Act: -0.0002
Data Index: 246725 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 2.2012. Min Range: -2.2012
Max Act: 1.8339. Min Act: -0.0002
Data Index: 329448 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full textTruncated
Full Text #19