Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 12 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.7183. Min Act: -0.0000
Data Index: 1580277 (Python Code)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.2932. Min Act: -0.0001
Data Index: 1633036 (Python Code)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.6764. Min Act: -0.0001
Data Index: 1557510 (Python Code)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.3007. Min Act: -0.0001
Data Index: 1591057 (Python Code)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.3858. Min Act: -0.0001
Data Index: 1436105 (Python Code)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.6119. Min Act: -0.0001
Data Index: 1410471 (Python Code)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.6821. Min Act: -0.0001
Data Index: 1443672 (Python Code)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.2513. Min Act: -0.0001
Data Index: 1594387 (Python Code)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.1579. Min Act: -0.0001
Data Index: 1610626 (Python Code)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7183. Min Range: -2.7183
Max Act: 1.7154. Min Act: -0.0001
Data Index: 1645014 (Python Code)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.1028. Min Act: -0.0000
Data Index: 1476807 (Python Code)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.0858. Min Act: -0.0001
Data Index: 1532452 (Python Code)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7183. Min Range: -2.7183
Max Act: 1.8692. Min Act: -0.0000
Data Index: 1517793 (Python Code)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7183. Min Range: -2.7183
Max Act: 1.8266. Min Act: -0.0001
Data Index: 1373355 (Python Code)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7183. Min Range: -2.7183
Max Act: 1.9450. Min Act: -0.0001
Data Index: 1601913 (Python Code)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.1165. Min Act: -0.0001
Data Index: 1466088 (Python Code)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.1362. Min Act: -0.0001
Data Index: 1560828 (Python Code)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.1172. Min Act: -0.0000
Data Index: 1453072 (Python Code)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.3387. Min Act: -0.0001
Data Index: 1508539 (Python Code)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7183. Min Range: -2.7183
Max Act: 2.1967. Min Act: -0.0000
Data Index: 1417247 (Python Code)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19