Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3173 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.0389. Min Range: -3.0389
Max Act: 3.0389. Min Act: -0.0001
Data Index: 1554629 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.7293. Min Act: -0.0001
Data Index: 1586860 (Python Code)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.5944. Min Act: -0.0001
Data Index: 1448229 (Python Code)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.5610. Min Act: -0.0001
Data Index: 1377006 (Python Code)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.4802. Min Act: -0.0001
Data Index: 1512097 (Python Code)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.5316. Min Act: -0.0001
Data Index: 1395842 (Python Code)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.5229. Min Act: -0.0001
Data Index: 1422887 (Python Code)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.4469. Min Act: -0.0001
Data Index: 1605864 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.3916. Min Act: -0.0001
Data Index: 1578601 (Python Code)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.4513. Min Act: -0.0001
Data Index: 1384954 (Python Code)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.2862. Min Act: -0.0001
Data Index: 1462050 (Python Code)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.1653. Min Act: -0.0001
Data Index: 1535585 (Python Code)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.2754. Min Act: -0.0001
Data Index: 1508395 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.2325. Min Act: -0.0001
Data Index: 1546267 (Python Code)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.1186. Min Act: -0.0001
Data Index: 1401125 (Python Code)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.1090. Min Act: -0.0001
Data Index: 1584489 (Python Code)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.0421. Min Act: -0.0001
Data Index: 1364128 (Python Code)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0389. Min Range: -3.0389
Max Act: 1.9195. Min Act: -0.0001
Data Index: 1374826 (Python Code)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.0129. Min Act: -0.0001
Data Index: 1637625 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0389. Min Range: -3.0389
Max Act: 2.1080. Min Act: -0.0001
Data Index: 1563761 (Python Code)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19