Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 5105 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.5445. Min Act: -0.0001
Data Index: 597916 (The Pile)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.4194. Min Act: -0.0001
Data Index: 725514 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.4860. Min Act: -0.0001
Data Index: 1383280 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.6483. Min Act: -0.0001
Data Index: 397541 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.6117. Min Act: -0.0001
Data Index: 1104513 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.2620. Min Act: -0.0001
Data Index: 971756 (The Pile)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.2198. Min Act: -0.0001
Data Index: 655012 (The Pile)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.3437. Min Act: -0.0001
Data Index: 111813 (The Pile)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.2580. Min Act: -0.0001
Data Index: 493455 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.2972. Min Act: -0.0001
Data Index: 1790227 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.4845. Min Act: -0.0001
Data Index: 54100 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.1312. Min Act: -0.0001
Data Index: 191643 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6483. Min Range: -1.6483
Max Act: 0.8881. Min Act: -0.0001
Data Index: 929181 (The Pile)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.3169. Min Act: -0.0001
Data Index: 564978 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.1203. Min Act: -0.0001
Data Index: 686868 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.2786. Min Act: -0.0001
Data Index: 429566 (The Pile)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.2740. Min Act: -0.0001
Data Index: 1259748 (The Pile)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.2583. Min Act: -0.0001
Data Index: 359649 (The Pile)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.1103. Min Act: -0.0001
Data Index: 431456 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6483. Min Range: -1.6483
Max Act: 1.1041. Min Act: -0.0001
Data Index: 1358230 (The Pile)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19