Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2727 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.0962. Min Range: -3.0962
Max Act: 3.0962. Min Act: -0.0001
Data Index: 718897 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.2197. Min Act: -0.0001
Data Index: 1403875 (Python Code)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.2785. Min Act: -0.0001
Data Index: 1578536 (Python Code)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.3233. Min Act: -0.0001
Data Index: 205849 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.5188. Min Act: -0.0001
Data Index: 1465712 (Python Code)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.3205. Min Act: -0.0001
Data Index: 1585495 (Python Code)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.1203. Min Act: -0.0001
Data Index: 1508743 (Python Code)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.3719. Min Act: -0.0001
Data Index: 1365808 (Python Code)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.1152. Min Act: -0.0001
Data Index: 1622196 (Python Code)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.0736. Min Act: -0.0001
Data Index: 410163 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.2283. Min Act: -0.0001
Data Index: 1564982 (Python Code)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.2416. Min Act: -0.0001
Data Index: 1368011 (Python Code)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.2255. Min Act: -0.0001
Data Index: 1627792 (Python Code)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.2764. Min Act: -0.0001
Data Index: 1402966 (Python Code)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.2778. Min Act: -0.0001
Data Index: 1457826 (Python Code)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.1431. Min Act: -0.0001
Data Index: 1373031 (Python Code)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.2526. Min Act: -0.0001
Data Index: 1125953 (C4 (Web Text))
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.1081. Min Act: -0.0001
Data Index: 1570363 (Python Code)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.1293. Min Act: -0.0001
Data Index: 1649851 (Python Code)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0962. Min Range: -3.0962
Max Act: 2.0416. Min Act: -0.0001
Data Index: 1532386 (Python Code)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19