Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2386 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.9757. Min Act: -0.0001
Data Index: 1545464 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.8918. Min Act: -0.0001
Data Index: 461525 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0265. Min Range: -1.0265
Max Act: 1.0265. Min Act: -0.0001
Data Index: 1556474 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.9325. Min Act: -0.0001
Data Index: 1570823 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.9864. Min Act: -0.0001
Data Index: 1363645 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.9226. Min Act: -0.0001
Data Index: 70099 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.9431. Min Act: -0.0001
Data Index: 920380 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.8514. Min Act: -0.0001
Data Index: 641303 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.8313. Min Act: -0.0001
Data Index: 1888328 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.9079. Min Act: -0.0001
Data Index: 443845 (The Pile)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.9061. Min Act: -0.0001
Data Index: 1717154 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.9223. Min Act: -0.0001
Data Index: 1414504 (The Pile)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.8614. Min Act: -0.0001
Data Index: 1573674 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.8015. Min Act: -0.0001
Data Index: 1052972 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.7992. Min Act: -0.0001
Data Index: 643690 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.8608. Min Act: -0.0001
Data Index: 1299766 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.8097. Min Act: -0.0001
Data Index: 740774 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.9028. Min Act: -0.0001
Data Index: 1685227 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.7960. Min Act: -0.0001
Data Index: 988380 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0265. Min Range: -1.0265
Max Act: 0.7998. Min Act: -0.0001
Data Index: 367521 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19