Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 777 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.1173. Min Range: -1.1173
Max Act: 1.1173. Min Act: -0.0001
Data Index: 1394873 (Python Code)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.9796. Min Act: -0.0001
Data Index: 1624835 (Python Code)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.8792. Min Act: -0.0001
Data Index: 1387799 (Python Code)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.8573. Min Act: -0.0001
Data Index: 1519388 (Python Code)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.8544. Min Act: -0.0001
Data Index: 1574968 (Python Code)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.8037. Min Act: -0.0001
Data Index: 1476624 (Python Code)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.8187. Min Act: -0.0001
Data Index: 1567159 (Python Code)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.7932. Min Act: -0.0001
Data Index: 1440774 (Python Code)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.8166. Min Act: -0.0001
Data Index: 1514155 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.7908. Min Act: -0.0001
Data Index: 1630215 (Python Code)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.8310. Min Act: -0.0001
Data Index: 1548884 (Python Code)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.8045. Min Act: -0.0001
Data Index: 1536735 (Python Code)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.8114. Min Act: -0.0001
Data Index: 1495062 (Python Code)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.7867. Min Act: -0.0001
Data Index: 1622604 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.7877. Min Act: -0.0001
Data Index: 1580059 (Python Code)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.7810. Min Act: -0.0001
Data Index: 1521290 (Python Code)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.7535. Min Act: -0.0001
Data Index: 1452756 (Python Code)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.7543. Min Act: -0.0001
Data Index: 1618006 (Python Code)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.7759. Min Act: -0.0001
Data Index: 1646136 (Python Code)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1173. Min Range: -1.1173
Max Act: 0.7716. Min Act: -0.0001
Data Index: 1494855 (Python Code)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19