Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3731 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.2539. Min Act: -0.0001
Data Index: 1700778 (The Pile)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.1856. Min Act: -0.0001
Data Index: 976485 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.0649. Min Act: -0.0001
Data Index: 1572057 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.0566. Min Act: -0.0001
Data Index: 405460 (The Pile)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.0737. Min Act: -0.0001
Data Index: 1348196 (The Pile)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.7061. Min Act: -0.0001
Data Index: 482645 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.9088. Min Act: -0.0001
Data Index: 694953 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.9894. Min Act: -0.0001
Data Index: 628875 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.9408. Min Act: -0.0001
Data Index: 144677 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.7742. Min Act: -0.0001
Data Index: 1287342 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.9308. Min Act: -0.0001
Data Index: 930688 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.8831. Min Act: -0.0001
Data Index: 1603528 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.9166. Min Act: -0.0001
Data Index: 274267 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.1456. Min Act: -0.0001
Data Index: 22412 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.7868. Min Act: -0.0001
Data Index: 579359 (The Pile)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.9159. Min Act: -0.0001
Data Index: 1258989 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.9291. Min Act: -0.0001
Data Index: 548150 (The Pile)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.0548. Min Act: -0.0001
Data Index: 454146 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.8348. Min Act: -0.0001
Data Index: 938604 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.8055. Min Act: -0.0001
Data Index: 1088203 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19