Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 756 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.1113. Min Range: -3.1113
Max Act: 3.1113. Min Act: -0.0001
Data Index: 1544212 (Python Code)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.9339. Min Act: -0.0001
Data Index: 1616471 (Python Code)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.8910. Min Act: -0.0001
Data Index: 1595876 (Python Code)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1113. Min Range: -3.1113
Max Act: 3.0141. Min Act: -0.0001
Data Index: 1432912 (Python Code)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.8517. Min Act: -0.0001
Data Index: 1604485 (Python Code)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.7446. Min Act: -0.0001
Data Index: 1633265 (Python Code)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.6430. Min Act: -0.0001
Data Index: 1646962 (Python Code)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.5794. Min Act: -0.0001
Data Index: 1442031 (Python Code)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.4687. Min Act: -0.0001
Data Index: 1651727 (Python Code)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.3945. Min Act: -0.0001
Data Index: 1538511 (Python Code)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.3906. Min Act: -0.0001
Data Index: 1646116 (Python Code)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.3730. Min Act: -0.0001
Data Index: 1653912 (Python Code)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.3699. Min Act: -0.0001
Data Index: 1547596 (Python Code)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.3751. Min Act: -0.0001
Data Index: 1588208 (Python Code)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.6984. Min Act: -0.0001
Data Index: 1397228 (Python Code)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.1781. Min Act: -0.0001
Data Index: 1453807 (Python Code)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.1609. Min Act: -0.0001
Data Index: 1369265 (Python Code)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.2578. Min Act: -0.0001
Data Index: 1614650 (Python Code)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.3763. Min Act: -0.0001
Data Index: 1496954 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1113. Min Range: -3.1113
Max Act: 2.3639. Min Act: -0.0001
Data Index: 1396119 (Python Code)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19