Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 550 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.1602. Min Range: -1.1602
Max Act: 1.1602. Min Act: -0.0001
Data Index: 655004 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1602. Min Range: -1.1602
Max Act: 1.1253. Min Act: -0.0001
Data Index: 1548194 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.9932. Min Act: -0.0001
Data Index: 1581285 (The Pile)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.9898. Min Act: -0.0001
Data Index: 1987675 (The Pile)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1602. Min Range: -1.1602
Max Act: 1.0210. Min Act: -0.0001
Data Index: 1719841 (The Pile)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.9692. Min Act: -0.0001
Data Index: 314502 (The Pile)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.9373. Min Act: -0.0001
Data Index: 59310 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.9363. Min Act: -0.0001
Data Index: 1662403 (The Pile)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.8879. Min Act: -0.0001
Data Index: 425204 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.9363. Min Act: -0.0001
Data Index: 184609 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.9254. Min Act: -0.0001
Data Index: 1477262 (The Pile)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.9228. Min Act: -0.0001
Data Index: 1063768 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.8590. Min Act: -0.0001
Data Index: 1604513 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.8642. Min Act: -0.0001
Data Index: 1587056 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.9666. Min Act: -0.0001
Data Index: 1831712 (The Pile)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.8645. Min Act: -0.0001
Data Index: 407266 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.8986. Min Act: -0.0001
Data Index: 1690559 (The Pile)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.9144. Min Act: -0.0001
Data Index: 445690 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.8166. Min Act: -0.0001
Data Index: 703216 (The Pile)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1602. Min Range: -1.1602
Max Act: 0.8480. Min Act: -0.0001
Data Index: 105851 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19