Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 430 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.8499. Min Act: -0.0001
Data Index: 336190 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.8427. Min Act: -0.0001
Data Index: 1269113 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7908. Min Act: -0.0001
Data Index: 1169824 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.9053. Min Act: -0.0001
Data Index: 817009 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.8106. Min Act: -0.0001
Data Index: 991059 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7316. Min Act: -0.0001
Data Index: 10747 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7426. Min Act: -0.0001
Data Index: 76344 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7392. Min Act: -0.0001
Data Index: 1000289 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7462. Min Act: -0.0001
Data Index: 1582110 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7404. Min Act: -0.0001
Data Index: 1705323 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7403. Min Act: -0.0001
Data Index: 299932 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7122. Min Act: -0.0001
Data Index: 1801671 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7052. Min Act: -0.0001
Data Index: 695051 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7536. Min Act: -0.0001
Data Index: 1655375 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.6503. Min Act: -0.0001
Data Index: 237174 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.6710. Min Act: -0.0001
Data Index: 1543689 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7387. Min Act: -0.0001
Data Index: 1881805 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.7250. Min Act: -0.0001
Data Index: 1991026 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.6559. Min Act: -0.0001
Data Index: 835844 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9053. Min Range: -0.9053
Max Act: 0.6283. Min Act: -0.0001
Data Index: 149260 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19