Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 807 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.1976. Min Act: -0.0001
Data Index: 672402 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 1206527 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 165356 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 911017 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 934402 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 77726 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 1353586 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 78244 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 972262 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 311366 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 120860 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 1534999 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 1889043 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 291862 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 86931 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0002
Data Index: 926811 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 1517188 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 1027618 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 1949866 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1976. Min Range: -1.1976
Max Act: 1.0906. Min Act: -0.0001
Data Index: 812284 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19