Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3907 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 50860 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0000
Data Index: 63131 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 60564 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 10731 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 54119 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 53544 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 52225 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 51912 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 51193 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 23538 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 26083 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 5831 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 43260 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 42087 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 39623 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 27228 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 13039 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 26586 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 1706 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0543. Min Range: -0.0543
Max Act: 0.0543. Min Act: -0.0001
Data Index: 26204 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19