Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4305 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.1262. Min Act: -0.0001
Data Index: 1486081 (Python Code)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.0808. Min Act: -0.0001
Data Index: 1419955 (Python Code)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.1661. Min Act: -0.0001
Data Index: 1636256 (Python Code)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.0743. Min Act: -0.0001
Data Index: 1551018 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.1555. Min Act: -0.0001
Data Index: 1639677 (Python Code)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.0571. Min Act: -0.0001
Data Index: 1476665 (Python Code)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.1533. Min Act: -0.0001
Data Index: 1646193 (Python Code)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2082. Min Range: -2.2082
Max Act: 1.9778. Min Act: -0.0001
Data Index: 1646143 (Python Code)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2082. Min Range: -2.2082
Max Act: 1.9484. Min Act: -0.0001
Data Index: 1442984 (Python Code)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.0353. Min Act: -0.0001
Data Index: 1584156 (Python Code)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.2082. Min Act: -0.0001
Data Index: 1642986 (Python Code)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.0212. Min Act: -0.0001
Data Index: 1600100 (Python Code)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.1070. Min Act: -0.0001
Data Index: 1504909 (Python Code)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2082. Min Range: -2.2082
Max Act: 1.8905. Min Act: -0.0001
Data Index: 1396543 (Python Code)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2082. Min Range: -2.2082
Max Act: 2.0725. Min Act: -0.0001
Data Index: 1406376 (Python Code)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2082. Min Range: -2.2082
Max Act: 1.9507. Min Act: -0.0001
Data Index: 1544017 (Python Code)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2082. Min Range: -2.2082
Max Act: 1.9925. Min Act: -0.0001
Data Index: 1388413 (Python Code)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2082. Min Range: -2.2082
Max Act: 1.8721. Min Act: -0.0001
Data Index: 1366591 (Python Code)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2082. Min Range: -2.2082
Max Act: 1.8848. Min Act: -0.0001
Data Index: 1456224 (Python Code)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2082. Min Range: -2.2082
Max Act: 1.9770. Min Act: -0.0001
Data Index: 1441805 (Python Code)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19