Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1897 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.9795. Min Act: -0.0000
Data Index: 908834 (The Pile)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.7863. Min Act: 0.0004
Data Index: 630763 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.8638. Min Act: 0.0004
Data Index: 627620 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.8656. Min Act: 0.0001
Data Index: 1510313 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.7419. Min Act: 0.0002
Data Index: 1187718 (The Pile)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.6927. Min Act: 0.0001
Data Index: 1571779 (The Pile)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.6464. Min Act: 0.0000
Data Index: 281765 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.6268. Min Act: 0.0004
Data Index: 1339861 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.6315. Min Act: -0.0000
Data Index: 439038 (The Pile)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.5880. Min Act: -0.0000
Data Index: 1588879 (The Pile)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.5823. Min Act: -0.0000
Data Index: 1118009 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.5704. Min Act: 0.0004
Data Index: 203745 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.5660. Min Act: -0.0000
Data Index: 828763 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.5672. Min Act: 0.0004
Data Index: 382836 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.5553. Min Act: 0.0004
Data Index: 564483 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.6862. Min Act: 0.0004
Data Index: 43698 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.3504. Min Act: 0.0004
Data Index: 702018 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.4782. Min Act: -0.0000
Data Index: 1021294 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.5987. Min Act: 0.0001
Data Index: 275145 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9795. Min Range: -2.9795
Max Act: 2.4695. Min Act: 0.0004
Data Index: 272603 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19