Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1617 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 4.6957. Min Range: -4.6957
Max Act: 4.0099. Min Act: -0.0000
Data Index: 1389821 (The Pile)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6957. Min Range: -4.6957
Max Act: 3.5185. Min Act: 0.0000
Data Index: 928012 (The Pile)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6957. Min Range: -4.6957
Max Act: 3.3850. Min Act: -0.0000
Data Index: 508375 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6957. Min Range: -4.6957
Max Act: 3.4524. Min Act: -0.0000
Data Index: 1241473 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6957. Min Range: -4.6957
Max Act: 3.1875. Min Act: -0.0000
Data Index: 1976900 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6957. Min Range: -4.6957
Max Act: 3.1536. Min Act: -0.0000
Data Index: 1368217 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6957. Min Range: -4.6957
Max Act: 4.6957. Min Act: -0.0000
Data Index: 1250437 (The Pile)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6957. Min Range: -4.6957
Max Act: 3.1159. Min Act: -0.0000
Data Index: 819196 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6957. Min Range: -4.6957
Max Act: 2.9560. Min Act: -0.0000
Data Index: 1043386 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6957. Min Range: -4.6957
Max Act: 3.1002. Min Act: -0.0000
Data Index: 279074 (The Pile)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6957. Min Range: -4.6957
Max Act: 3.0969. Min Act: 0.0000
Data Index: 308689 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6957. Min Range: -4.6957
Max Act: 2.9109. Min Act: -0.0000
Data Index: 78012 (The Pile)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6957. Min Range: -4.6957
Max Act: 3.1900. Min Act: -0.0000
Data Index: 527445 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6957. Min Range: -4.6957
Max Act: 2.6787. Min Act: -0.0000
Data Index: 1641009 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6957. Min Range: -4.6957
Max Act: 2.9584. Min Act: -0.0000
Data Index: 249649 (The Pile)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6957. Min Range: -4.6957
Max Act: 2.9773. Min Act: -0.0000
Data Index: 145673 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6957. Min Range: -4.6957
Max Act: 2.9470. Min Act: -0.0000
Data Index: 754108 (The Pile)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6957. Min Range: -4.6957
Max Act: 2.6284. Min Act: 0.0000
Data Index: 145310 (The Pile)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6957. Min Range: -4.6957
Max Act: 2.7100. Min Act: -0.0000
Data Index: 578646 (The Pile)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6957. Min Range: -4.6957
Max Act: 2.7279. Min Act: -0.0000
Data Index: 1535666 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19